© 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. 55724
    Prev
    Next
    INDEX
    Explanations

    html meta link tags

    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
    quared
    -0.08
    èĢģ天
    -0.07
    ike
    -0.07
    ç±³äºļ
    -0.07
    æŁ¥æĶ¶
    -0.07
    (!$
    -0.07
    ç»´æĸ¯
    -0.07
    य
    -0.07
    çļĦå°±æĺ¯
    -0.07
    itamente
    -0.07
    POSITIVE LOGITS
    FullName
    0.07
    主æĦı
    0.07
    åľ¨å¹³æŶ
    0.07
    etag
    0.07
    åIJĮ人
    0.06
    InitialState
    0.06
    à¸ĵา
    0.06
    aches
    0.06
    éĩįå·¥
    0.06
    ÑĮев
    0.06
    Activations Density 0.074%

    No Known Activations