{"total":20,"rows":[{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"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":"2507.23784","title":"SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2603.07343","title":"Learning Concept Bottleneck Models from Mechanistic Explanations","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2504.06486","title":"Mind the (Data) Gap: Evaluating Vision Systems in Small Data Applications","created":"2025-04-08","cited_by_count":3,"area":null},{"id":"2508.03649","title":"Cross-Model Semantics in Representation Learning","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2510.14053","title":"Position: Require Frontier AI Labs To Release Small \"Analog\" Models","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2605.13675","title":"Characterizing Universal Object Representations Across Vision Models","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2512.07245","title":"Zero-Shot Textual Explanations via Translating Decision-Critical Features","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2606.09653","title":"A Unifying Framework for Concept-Based Representational Similarity","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2505.23917","title":"Representational Difference Explanations","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2605.20337","title":"Capability $\\neq$ Interpretability: Human Interpretability of Vision Foundation Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.26921","title":"Similarity-based representation factorization for revealing interpretable dimensions in representational data","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.07882","title":"The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.16897","title":"Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architectures","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2609.04721","title":"Locating and Steering Refusal Beyond Attention","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.05399","title":"From Interpretability Methods to Interpretable Models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.13198","title":"SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.31996","title":"Can Circuit Alignment Predict OOD Generalization?","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}