Interpretability | Ravid Shwartz-Zivhttps://www.ravid-shwartz-ziv.com/tag/interpretability/InterpretabilitySource Themes Academic (https://sourcethemes.com/academic/)en-usThu, 11 Jun 2026 19:51:44 +0000https://www.ravid-shwartz-ziv.com/img/ravid-shwartz-ziv-social-v2.pngInterpretabilityhttps://www.ravid-shwartz-ziv.com/tag/interpretability/Mirage Probes: How Vision Models Fake Visual Understandinghttps://www.ravid-shwartz-ziv.com/publication/mirage-probes/Thu, 11 Jun 2026 19:51:44 +0000https://www.ravid-shwartz-ziv.com/publication/mirage-probes/Exploring Human-AI Conceptual Alignment through the Prism of Chesshttps://www.ravid-shwartz-ziv.com/publication/chess-conceptual-alignment/Wed, 29 Oct 2025 00:00:00 +0000https://www.ravid-shwartz-ziv.com/publication/chess-conceptual-alignment/Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coinhttps://www.ravid-shwartz-ziv.com/publication/attention-sinks-compression-valleys/Tue, 07 Oct 2025 21:27:24 +0000https://www.ravid-shwartz-ziv.com/publication/attention-sinks-compression-valleys/Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Traininghttps://www.ravid-shwartz-ziv.com/publication/layer-importance-math-reasoning/Fri, 27 Jun 2025 21:04:55 +0000https://www.ravid-shwartz-ziv.com/publication/layer-importance-math-reasoning/