© 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. 43568
    Prev
    Next
    INDEX
    Explanations

    as a X

    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
    imonial
    -0.08
    hower
    -0.08
     dite
    -0.08
    举ä¸ĸ
    -0.08
    wujudkan
    -0.08
    è°ĵä¹ĭ
    -0.07
    itals
    -0.07
    éħĴå±ĭ
    -0.07
    声åIJį
    -0.07
    illard
    -0.07
    POSITIVE LOGITS
    ä¸Ģç§į
    0.08
    ä¸Ģ種
    0.07
     integral
    0.07
    yin
    0.07
    ä¸įä»ħä»ħæĺ¯
    0.07
    ä¸įäºĮ
    0.07
    ç«ĭ
    0.07
    æĺ¯ä¸Ģç§į
    0.07
    è£
    0.06
    ä¸ĢåĽŀäºĭ
    0.06
    Activations Density 0.176%

    No Known Activations