© 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. 58528
    Prev
    Next
    INDEX
    Explanations

    code and punctuation delimiters

    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
    为代表çļĦ
    -0.07
    è¿ĺæĺ¯ä¸ª
    -0.07
    heel
    -0.07
    imat
    -0.07
    STRU
    -0.07
    ç§ijåѦä¸İæĬĢæľ¯
    -0.06
    uart
    -0.06
     ÏĢο
    -0.06
    ç®ĹäºĨ
    -0.06
    æĹłæ¯Ĵ
    -0.06
    POSITIVE LOGITS
    queira
    0.08
    åĮ¡
    0.08
    §
    0.08
    ptrdiff
    0.08
    ä¸Ķ
    0.07
    qip
    0.07
    åīįéĿ¢çļĦ
    0.07
    éļĻ
    0.06
    reu
    0.06
    atten
    0.06
    Activations Density 0.006%

    No Known Activations