© 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. 11614
    Prev
    Next
    INDEX
    Explanations

    structure diagrams, images, or text

    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
    åľ¨åIJĦç§į
    -0.07
    åľ¨æŁIJäºĽ
    -0.07
    ä¸įå®ļæľŁ
    -0.07
    æ¡Įä¸ĬçļĦ
    -0.07
    æŁIJäºĽ
    -0.07
    说ä¸įå®ļ
    -0.07
    åĵįåºĶ
    -0.06
    åĩĿ
    -0.06
    åĽłä¸ºå®ĥ们
    -0.06
    åĵį
    -0.06
    POSITIVE LOGITS
    æĺ¥æļĸèĬ±å¼Ģ
    0.08
    æĺ¥æĿ¥
    0.08
    রà§įত
    0.08
    utnik
    0.08
     gá»ĵm
    0.07
     íģ¬ê²Į
    0.07
     Examiner
    0.07
    itar
    0.07
    à¹Ģà¸ĸ
    0.07
    มà¸Ļà¸ķรี
    0.07
    Activations Density 0.100%

    No Known Activations