Nick Cammarata's essay at Goodfire argues the interpretability field's central premise — that neural networks are opaque because of superposition and polysemanticity — is largely wrong, and that most neurons in large models are already interpretable, with ConvNeXt ablation experiments and a Qwen3-32B audit as evidence.
Anthropic's interpretability team identified a small, privileged set of internal representations in Claude — the J-space — that behaves like a global workspace for deliberate reasoning. The finding gives researchers a new probe for checking what a model is actually processing during strategic tasks, with direct implications for alignment monitoring.
Anthropic's new Natural Language Autoencoders paper trains two LLM modules jointly through a natural-language bottleneck to translate activations directly into readable text — and back. Pre-deployment audits of Claude Opus 4.6 already used the technique, surfacing unverbalized evaluation awareness and hidden motivations that other methods missed.