© 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. 10238
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å¾Ĺ天
    -0.08
    追究
    -0.07
    å¾Ĺå¿ĥ
    -0.07
    áĭ¨
    -0.07
    uling
    -0.07
    //*[
    -0.07
    å¾·åŁº
    -0.07
    itled
    -0.07
    ä¹IJçļĦ
    -0.07
     Vara
    -0.06
    POSITIVE LOGITS
    æĪ¿å®¢
    0.06
     Saud
    0.06
    illen
    0.06
     Howe
    0.06
    æķ´å½¢å¤ĸç§ij
    0.06
    .GetLength
    0.06
    å®¡æł¸åIJİ
    0.06
    wes
    0.06
     Champ
    0.06
    ä»İ头
    0.06
    Activations Density 0.000%

    No Known Activations