新闻
Can open models carry readable silent signals before they speak? Reproducing J-Lens Readouts on Kimi K3 & Qwen3.5-9B
Fireworks AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- Researchers applied J-Lens probes to open models Kimi K3 and Qwen3.5-9B, detecting task-relevant vocabulary in hidden states before models generate visible output tokens.
- 为何重要
- Matters for engineers building interpretability tools, debugging model behavior, or understanding what models compute internally during inference.
- 注意
- Method relies on fitted probes trained on calibration data; results depend on tokenizer choices and may not generalize across all model architectures or tasks.
收听本摘要
- qwen
- kimi
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。