On Qwen, the J-lens readouts at the newline token reveal lies

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.

Analyze with AIAnalyze with ChatGPTAnalyze with ClaudeAnalyze with PerplexityAnalyze with Google AI ModeAnalyze with GrokAnalyze with Microsoft Copilot