© 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. 19195
    Prev
    Next
    INDEX
    Explanations

    python module

    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
     ourselves
    -0.07
    æŃ¥
    -0.07
    ativas
    -0.06
    imbul
    -0.06
    perms
    -0.06
    <?,
    -0.06
    endr
    -0.06
    ç¯Ŀ
    -0.06
    attes
    -0.06
    åĨħåĬĽ
    -0.06
    POSITIVE LOGITS
    clare
    0.07
    æĹ¥ä»¥æĿ¥
    0.07
    qua
    0.07
    ãģĤãģı
    0.07
    éĥ½æĺ¯èĩªå·±
    0.07
    uoja
    0.07
    ër
    0.07
    ewood
    0.07
    åľ°ç¨İ
    0.07
    ç»ĻæĪijçķĻè¨Ģ
    0.07
    Activations Density 0.615%

    No Known Activations