Efficient Auto-Interpretability of AI Models in Biology

[2608.27754] Efficient Auto-Interpretability of AI Models in Biology Skip to main content Search Submit Donate Log in Quantitative Biology > Quantitative Methods arXiv:2608.27754 (q-bio) [Submitted on 27 Aug 2026] Title: Efficient Auto-Interpretability of AI Models in Biology Authors: Piotr Jedryszek , Oliver M. Crook View PDF HTML (experimental) Abstract: Sparse autoencoders (SAEs), and other interpretability methods could turn AI models in Biology and other fields into engines of scientific discovery by explaining the superhuman capabilities of those models. However, a latent is only useful if we know three things: whether it is coherent, whether it can be described, and whether that description has predictive power. These questions are routinely conflated. We assemble them into a single pipeline and report the practical innovations each stage required. First, cross-seed dictionary stability prioritises which latents are worth spending resources to investigate. Second, an intruder-detection task asks whether a latents activating examples share a recognizable pattern. Third, a separate pass proposes a candidate biological description which we convert into falsifiable predictions which can be tested in silico. Deployed on the Boltz-1 Pairformer trunk, stability prioritisation finds interpretable latents using about 4.4 times fewer latent evaluations each, and at 5.2 times lower measured cost, while recovering over half of them, and the external check shows the surfaced motifs are significantly enriched for their claimed annotations. The results also suggest a possible tension: the cross- seed stability might be selecting for some types of features, like structure-related ones, much more than others, such as function-related features. Subjects: Quantitative Methods (q-bio.QM) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2608.27754 [q-bio.QM] (or arXiv:2608.27754v1 [q-bio.QM] for this version) https://doi.org/10.48550/arXiv.2608.27754 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Piotr Jedryszek [ view email ] [v1] Thu, 27 Aug 2026 22:32:43 UTC (169 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: q-bio.QM < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI q-bio References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Efficient Auto-Interpretability of AI Models in Biology#779674
• AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery#144352
• OpenScientist: evaluating an open agentic AI co-scientist to accelerate biomedical discovery#18838
• SCIRIGOR:Evaluating Open-Ended Scientific Analysis Beyond Final Scores#973792
• Quantitative Evidence Mining for Plausibility-Aware Biomedical AI#799597