© 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. 3404
    Prev
    Next
    INDEX
    Explanations

    family of

    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
    ä¸Ģ声
    -0.08
    اتÙħ
    -0.07
    ิล
    -0.07
    ×ķ
    -0.07
    _DU
    -0.07
    æĺİäºĨ
    -0.07
    assen
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    idental
    -0.07
    xit
    -0.07
    POSITIVE LOGITS
    ergus
    0.08
    ergen
    0.07
    hood
    0.07
    次çļĦ
    0.07
    0.07
    uge
    0.07
    ën
    0.07
    -wide
    0.07
    大åĬ¿
    0.07
    buster
    0.07
    Activations Density 0.070%

    No Known Activations