© 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. 63322
    Prev
    Next
    INDEX
    Explanations

    digit or separator

    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
     ê
    -0.06
    amp
    -0.05
    amber
    -0.05
    åĽŀå¸ĸ
    -0.05
    缨
    -0.05
    tent
    -0.05
    taja
    -0.05
    Soft
    -0.05
    åij¼åIJ¸åĽ°éļ¾
    -0.05
    tec
    -0.05
    POSITIVE LOGITS
    burger
    0.09
    aturi
    0.08
    raison
    0.08
    avan
    0.08
    kert
    0.08
    ceso
    0.08
    æľĿ
    0.08
    versa
    0.08
    ullan
    0.08
    .kr
    0.08
    Activations Density 0.184%

    No Known Activations