{"total":6,"rows":[{"id":"2509.20393","title":"The Secret Agenda: LLMs Strategically Lie and Our Current Safety Tools Are Blind","created":"2025-09-23","cited_by_count":8,"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":"2506.01042","title":"Probing Neural Topology of Large Language Models","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2606.11722","title":"ICA Lens: Interpreting Language Models Without Training Another Dictionary","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2606.07714","title":"Beyond Accuracy: Interpreting Topic Representation in Suicide Ideation Detection Models","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2512.10720","title":"Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality","created":"2025-12-11","cited_by_count":0,"area":null}],"next_cursor":null}