© 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. 37898
    Prev
    Next
    INDEX
    Explanations

    assigning variable values

    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
    é¢Ŀå¤ĸ
    -0.08
     additional
    -0.07
    additional
    -0.07
    é¢Ŀå¤ĸçļĦ
    -0.07
     tambahan
    -0.07
    .removeChild
    -0.07
    é¡įå¤ĸ
    -0.07
    еÑĤо
    -0.07
    touch
    -0.07
    extra
    -0.06
    POSITIVE LOGITS
    úi
    0.08
    Slot
    0.07
     dota
    0.07
    ç»Ŀ大éĥ¨åĪĨ
    0.07
    ialized
    0.07
    æľīåĽ°éļ¾
    0.07
    apie
    0.07
    _slot
    0.07
    antie
    0.07
    Api
    0.07
    Activations Density 0.110%

    No Known Activations