{"total":66,"rows":[{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61,"area":"mechinterp"},{"id":"2504.14218","title":"Understanding the Repeat Curse in Large Language Models from a Feature Perspective","created":"2025-04-19","cited_by_count":37,"area":"mechinterp"},{"id":"2506.23845","title":"Position: Use Sparse Autoencoders to Discover Unknowns","created":"2025-06-30","cited_by_count":19,"area":"mechinterp"},{"id":"2502.17504","title":"Protein Large Language Models: A Comprehensive Survey","created":"2025-02-21","cited_by_count":18,"area":null},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16,"area":null},{"id":"2502.12352","title":"Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs","created":"2025-02-17","cited_by_count":13,"area":"mechinterp"},{"id":"2505.18186","title":"Discovering and Steering Interpretable Concepts in Large Generative Music Models","created":"2025-05-18","cited_by_count":13,"area":"mechinterp"},{"id":"2503.08764","title":"Towards Interpretable Protein Structure Prediction with Sparse Autoencoders","created":"2025-03-11","cited_by_count":12,"area":"mechinterp"},{"id":"2512.24440","title":"Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical features","created":"2025-12-30","cited_by_count":12,"area":null},{"id":"2510.00404","title":"AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2602.05027","title":"AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders","created":"2026-02-04","cited_by_count":8,"area":"mechinterp"},{"id":"2501.02393","title":"Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers","created":"2025-01-04","cited_by_count":7,"area":null},{"id":"2501.10282","title":"Computational Protein Science in the Era of Large Language Models (LLMs)","created":"2025-01-17","cited_by_count":6,"area":null},{"id":"2506.07459","title":"ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning","created":"2025-06-09","cited_by_count":6,"area":"deeprl"},{"id":"2602.00782","title":"Controlling Repetition in Protein Language Models","created":"2026-01-31","cited_by_count":5,"area":null},{"id":"2605.13930","title":"Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders","created":"2026-05-13","cited_by_count":5,"area":"mechinterp"},{"id":"2508.18567","title":"Sparse Autoencoders for Low-$N$ Protein Function Prediction and Design","created":"2025-08-25","cited_by_count":4,"area":"mechinterp"},{"id":"2607.12474","title":"From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery","created":"2026-07-14","cited_by_count":4,"area":"wm"},{"id":"2508.09363","title":"Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders","created":"2025-08-12","cited_by_count":3,"area":"lr"},{"id":"2509.05309","title":"ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders","created":"2025-08-26","cited_by_count":3,"area":"mechinterp"},{"id":"2512.05534","title":"A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima","created":"2025-12-05","cited_by_count":3,"area":"mechinterp"},{"id":"2602.12026","title":"Protein Circuit Tracing via Cross-layer Transcoders","created":"2026-02-12","cited_by_count":3,"area":"mechinterp"},{"id":"2411.15418","title":"Scaling Structure Aware Virtual Screening to Billions of Molecules with SPRINT","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2507.12950","title":"Insights into a radiology-specialised multimodal large language model with sparse autoencoders","created":"2025-07-17","cited_by_count":2,"area":"mllm"},{"id":"2509.24895","title":"Towards Understanding the Shape of Representations in Protein Language Models","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.21464","title":"CXR-LanIC: Language-Grounded Interpretable Classifier for Chest X-Ray Diagnosis","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2510.25807","title":"Discovering Interpretable Biological Concepts in Single-cell RNA-seq Foundation Models","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2512.08077","title":"Unveiling Latent Knowledge in Chemistry Language Models through Sparse Autoencoders","created":"2025-12-08","cited_by_count":2,"area":"mechinterp"},{"id":"2512.09757","title":"Circuits, Features, and Heuristics in Molecular Transformers","created":"2025-12-10","cited_by_count":2,"area":"mechinterp"},{"id":"2602.06020","title":"Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2602.20449","title":"Protein Language Models Diverge from Natural Language: Comparative Analysis and Improved Inference","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2603.04045","title":"Inference-Time Toxicity Mitigation in Protein Language Models","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2605.31518","title":"On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders","created":"2026-05-29","cited_by_count":2,"area":"mechinterp"},{"id":"2606.23443","title":"What Does a Chemical Language Model Know About Molecules?","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2608.12036","title":"Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2504.07156","title":"PLM-eXplain: Divide and Conquer the Protein Embedding Space","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2507.06458","title":"Automated Neuron Labelling Enables Generative Steering and Interpretability in Protein Language Models","created":"2025-07-08","cited_by_count":1,"area":"mechinterp"},{"id":"2602.23179","title":"Induction Meets Biology: Mechanisms of Repeat Detection in Protein Language Models","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2605.16331","title":"Retrieval and competition: how a protein foundation model starts a protein","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2606.07007","title":"A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders","created":"2026-06-05","cited_by_count":1,"area":"mechinterp"},{"id":"2606.10080","title":"VFUSE: Virulent Feature Understanding with Sparse autoEncoders","created":"2026-06-08","cited_by_count":1,"area":"mechinterp"},{"id":"2607.01336","title":"Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders","created":"2026-07-01","cited_by_count":1,"area":"mechinterp"},{"id":"2608.11475","title":"Probing and steering biology across Boltz-1s trunk-diffusion boundary","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2510.01252","title":"GPT and Prejudice: A Sparse Approach to Understanding Learned Representations in Large Language Models","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.01632","title":"BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.02734","title":"SAE-RNA: A Sparse Autoencoder Model for Interpreting RNA Language Model Representations","created":"2025-10-03","cited_by_count":0,"area":"mechinterp"},{"id":"2511.09432","title":"Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data","created":"2025-11-12","cited_by_count":0,"area":"mechinterp"},{"id":"2511.14781","title":"Quantifying the Role of OpenFold Components in Protein Structure Prediction","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2512.05794","title":"Mechanistic Interpretability of Antibody Language Models Using SAEs","created":"2025-12-05","cited_by_count":0,"area":"mechinterp"},{"id":"2602.01845","title":"No Generation without Representation: Efficient Causal Protein Language Models Enable Zero-Shot Fitness Estimation","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2604.14796","title":"PUFFIN: Protein Unit Discovery with Functional Supervision","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2606.12609","title":"Viral Proteins Reveal Geometry of Protein Language Models","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.16044","title":"Circuit Tracing in Autoregressive Protein Language Models","created":"2026-06-14","cited_by_count":0,"area":"mechinterp"},{"id":"2606.21876","title":"Protein contacts are already in the attention: a single-forward-pass alternative to the Categorical Jacobian","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2606.27440","title":"PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding","created":"2026-06-25","cited_by_count":0,"area":"mechinterp"},{"id":"2607.25244","title":"CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.27404","title":"ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.23626","title":"A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.25548","title":"Interpreting Protein Language Model Embeddings via Orthogonal Projection for Protein Fitness Prediction","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.26419","title":"Interpreting Latent Protein Language Model Features with Geometric Annotations","created":"2026-08-26","cited_by_count":0,"area":"mechinterp"},{"id":"2608.27754","title":"Efficient Auto-Interpretability of AI Models in Biology","created":"2026-08-27","cited_by_count":0,"area":"mechinterp"},{"id":"2609.16213","title":"Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.17736","title":"Machine learning kinetics from molecular dynamics data","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.35351","title":"Interference Beyond Geometry in Concept Extraction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.03029","title":"SoftGene: Protein Language Model-Enhanced Soft Prompting for Interpretable Gene Set Annotation","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05518","title":"What Does Fr\\'echet Distance Measure? A Directional Decomposition","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}