© 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. 38566
    Prev
    Next
    INDEX
    Explanations

    derivative of a variable with respect to another

    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
    åĽŀçŃĶéĩı
    -0.09
    oyer
    -0.09
    unga
    -0.09
    udou
    -0.09
    å·´åĭĴ
    -0.08
     Downs
    -0.08
    绯
    -0.08
    å¾ĺ
    -0.08
    åĽłæĤ¨çļĦ
    -0.08
    elson
    -0.08
    POSITIVE LOGITS
    èĴĻ
    0.06
     sÃłng
    0.05
    产
    0.05
     Math
    0.05
     Opr
    0.05
    çĮ®ç»Ļ
    0.05
    æĺ¯ä¸ª
    0.05
    å¤įæĿĤ
    0.05
    воÑĢ
    0.05
    åĿª
    0.05
    Activations Density 0.001%

    No Known Activations