© 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. 38106
    Prev
    Next
    INDEX
    Explanations

    in mathematical contexts

    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
    ئ
    -0.07
    asco
    -0.07
    akat
    -0.07
    æĸ°åĬłåĿ¡
    -0.06
    ת×Ļ
    -0.06
    ucker
    -0.06
    ä¸Ģè§Ĵ
    -0.06
    teman
    -0.06
    Ñģпа
    -0.06
    OnChange
    -0.06
    POSITIVE LOGITS
    夫æĸ¯åŁº
    0.08
    ãģ¯ãģļ
    0.08
    åĩ«
    0.07
    å¤§ä½ľ
    0.07
    arius
    0.07
    大æĺİ
    0.07
    ipel
    0.07
    ingers
    0.07
    inger
    0.07
    ners
    0.07
    Activations Density 0.010%

    No Known Activations