© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29164
    Prev
    Next
    INDEX
    Explanations

    too / same / familiar / obvious / ordered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĻĮçĶŁ
    -0.08
    rift
    -0.08
    onium
    -0.08
    ä¸įåľ¨ä¹İ
    -0.07
    ä¹±
    -0.07
    rafted
    -0.07
    _console
    -0.07
    å½¢å¼ıå¤ļæł·çļĦ
    -0.07
    ä¹Łä¸įçŁ¥
    -0.07
    ä¸įéĹ®
    -0.07
    POSITIVE LOGITS
    鼷åIJĮ
    0.11
    ãģ£ãģ¦ãģĹãģ¾ãģĨ
    0.09
    åĩłä¹İæīĢæľī
    0.09
    åįķä¸Ģ
    0.09
    åIJĮè´¨
    0.09
    è¿ĩäºİ
    0.09
     demais
    0.08
    ãģ«ãģªãģ£ãģ¦ãģĹãģ¾ãģĨ
    0.08
    -too
    0.08
    缺ä¹ı
    0.08
    Activations Density 0.149%

    No Known Activations