© 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. 25234
    Prev
    Next
    INDEX
    Explanations

    reserved .App

    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
     Niger
    -0.08
    æ¶
    -0.08
     Gupta
    -0.07
     Sharma
    -0.06
    红河
    -0.06
    chel
    -0.06
     Romanian
    -0.06
    ä¿Ŀå®ļ
    -0.06
    æŁ³
    -0.06
    imes
    -0.06
    POSITIVE LOGITS
    åĬłå·ŀ
    0.15
     Cupertino
    0.15
    åľ¨æ·±åľ³
    0.15
     Calif
    0.15
     California
    0.14
     Californ
    0.14
     Monterey
    0.14
    California
    0.14
    .apple
    0.14
     Yosemite
    0.13
    Activations Density 1.351%

    No Known Activations