© 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. 25427
    Prev
    Next
    INDEX
    Explanations

    numerical scores, mathematical expressions, or code definitions

    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
    ead
    -0.07
    <|box_end|>
    -0.07
    ฯ
    -0.06
    å©¢
    -0.06
    åĤij
    -0.06
    olet
    -0.06
    aine
    -0.06
    ç±ģ
    -0.06
     betr
    -0.06
    kland
    -0.06
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩåīį
    0.08
    ares
    0.07
    _processors
    0.07
    å¾Īæĥ³
    0.07
     chiêm
    0.07
    àºŃàºĩ
    0.07
    å¸ĮæľĽåı¯ä»¥
    0.07
    zyman
    0.06
    ìĿ¼ë¡ľ
    0.06
    ftype
    0.06
    Activations Density 0.058%

    No Known Activations