© 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. 29504
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

    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
    次äºİ
    -0.07
    StateException
    -0.07
     pend
    -0.07
    วิล
    -0.06
    uil
    -0.06
    è¿ĺæĺ¯ä¸Ģ
    -0.06
    fällig
    -0.06
    åħ¼æĢ»ç»ıçIJĨ
    -0.06
    ãģ¨ãĤĤ
    -0.06
    ith
    -0.06
    POSITIVE LOGITS
     alp
    0.08
    aç
    0.08
    acol
    0.07
    yms
    0.06
     Taille
    0.06
    æľīãĤĬ
    0.06
    æ·±æľī
    0.06
     sopr
    0.06
    Sur
    0.06
    dash
    0.06
    Activations Density 0.003%

    No Known Activations