© 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. 9890
    Prev
    Next
    INDEX
    Explanations

    control valve, closure unit, lift arms, access point

    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
    elm
    -0.06
    ikko
    -0.06
    æį²
    -0.06
     Liberties
    -0.06
    oen
    -0.05
    enum
    -0.05
    åĬĿ
    -0.05
    ummer
    -0.05
    纫
    -0.05
    cor
    -0.05
    POSITIVE LOGITS
    nado
    0.08
    æľ¨é½IJ
    0.08
    ,ll
    0.07
    ÏĢή
    0.07
    ī´
    0.07
     renomm
    0.07
    bolo
    0.07
    æĤ¨çİ°åľ¨çļĦä½įç½®
    0.07
    ANTI
    0.07
    kev
    0.07
    Activations Density 0.228%

    No Known Activations