https://ray-che.com/tags/interpretability/ Recent content in interpretability on Xijia Che Hugo -- gohugo.io en-us Mon, 27 Jul 2026 00:00:00 +0800 https://ray-che.com/posts/toy-models/ Mon, 27 Jul 2026 00:00:00 +0800 https://ray-che.com/posts/toy-models/ A replication of core claims about superposition in toy models, with an interactive animation of a PGD adversarial attack unfolding in the model’s latent space.