© 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. 41252
    Prev
    Next
    INDEX
    Explanations

    services to provide

    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
    -regexp
    -0.08
    è´£ç¼ĸ
    -0.08
    æĸĹç½Ĺ
    -0.08
    æĸ¹éĿ¢æľī
    -0.08
    /gpl
    -0.08
    ulen
    -0.08
    artos
    -0.08
    -Oct
    -0.07
    erness
    -0.07
    .getLength
    -0.07
    POSITIVE LOGITS
    ppy
    0.06
    åd
    0.06
    engl
    0.06
    óx
    0.06
    ç¡Ŀ
    0.06
    æııè¿°
    0.06
    ãĢĭ
    0.06
    eru
    0.06
    erb
    0.05
    åħ©åĢĭ人
    0.05
    Activations Density 0.122%

    No Known Activations