Neuralese

Creator

Creator

Seonglae Cho

Created

Created

2025 Dec 27 23:54

Editor

Editor

Seonglae Cho

Edited

Edited

2025 Dec 27 23:56

Refs

Refs

Latent Prompting

Internal Interface Theory

Latent Communication, Latent Reasoning

Thinking with continuous vectors

blackbox or not

Can we interpret latent reasoning using current mechanistic interpretability tools? — AI Alignment Forum

Authors: Bartosz Cywinski*, Bart Bussmann*, Arthur Conmy**, Joshua Engels**, Neel Nanda**, Senthooran Rajamanoharan** …

Can we interpret latent reasoning using current mechanistic interpretability tools? — AI Alignment Forum

https://www.alignmentforum.org/posts/YGAimivLxycZcqRFR/can-we-interpret-latent-reasoning-using-current-mechanistic#How_many_latent_vectors_does_the_model_actually_use_

Can we interpret latent reasoning using current mechanistic interpretability tools? — AI Alignment Forum

Backlinks

Mechanistic interpretability Activation Engineering Interpretable AI

Recommendations

//////