On Qwen, the J-lens readouts at the newline token reveal lies
Source ↗
👁 0
💬 0
1. TL;DRWe put four models (Qwen3.6-27B, two Gemma-3 models, gpt-oss-20b) in MASK's pressure scenarios, where a system prompt gives the model a role and a reason to lie about a fact it was told. We read the residual stream at the chat-template tokens with the J-lens. Then we grouped the readout words by their meaning into families and counted how often each family appears after lies and after truths.At the newline token right after Qwen's response, the lie family appears after 84% of lies and 9%
Comments (0)