© 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. 4452
    Prev
    Next
    INDEX
    Explanations

    file extensions or domain names

    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
    oux
    -0.09
    两个æĸ¹éĿ¢
    -0.08
    两æĸ¹éĿ¢
    -0.08
    óri
    -0.07
    æľī两ç§į
    -0.07
    isca
    -0.07
    éĢĻåħ©
    -0.07
    两ç§įæĸ¹å¼ı
    -0.07
    orian
    -0.07
     обоиÑħ
    -0.07
    POSITIVE LOGITS
     etc
    0.13
    çŃīåIJĦç§į
    0.12
    æ¯Ķå¦Ĥ
    0.12
    诸å¦Ĥ
    0.11
    çļĦåIJĦç§į
    0.10
    çŃīéĥ½æĺ¯
    0.10
    åIJĦç§į
    0.10
    ä¾ĭå¦Ĥ
    0.10
    æ¯Ķå¦Ĥ说
    0.10
    管çIJĨçŃī
    0.10
    Activations Density 0.268%

    No Known Activations