© 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. 64394
    Prev
    Next
    INDEX
    Explanations

    program variables, types, and 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
    ÏĨÏīν
    -0.07
    áŁĭ
    -0.06
    輩
    -0.06
    esp
    -0.06
    olan
    -0.06
    å¦Ĥèį¼
    -0.06
    ä¸į离
    -0.06
    åħ¨åĽ½äººæ°ij
    -0.06
    æı´æľĿ
    -0.06
    æīĢæĢĿ
    -0.06
    POSITIVE LOGITS
    agia
    0.08
    ivre
    0.07
    nock
    0.07
    igue
    0.07
    à¸Ńà¸Ķ
    0.07
    opsis
    0.07
    asio
    0.07
    teria
    0.06
     تÙĨا
    0.06
    ANDOM
    0.06
    Activations Density 0.210%

    No Known Activations