© 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. 49402
    Prev
    Next
    INDEX
    Explanations

    word in sentence, line, link, message, cookie

    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
    åIJĴ
    -0.08
    .rawValue
    -0.08
    aner
    -0.08
    elos
    -0.07
    æľī好çļĦ
    -0.07
    æĿ·
    -0.07
     Corm
    -0.07
    umni
    -0.07
    igts
    -0.07
    ;m
    -0.07
    POSITIVE LOGITS
    Sao
    0.07
    eku
    0.06
    è£ĺ
    0.06
    åĴĮ社ä¼ļä¿Ŀéļľ
    0.06
    Å¡in
    0.06
    æĪijä¸Ģå®ļä¼ļ
    0.06
    åŃľ
    0.06
    åľŁçŁ³
    0.06
    Ãŀ
    0.06
    äºīæī§
    0.06
    Activations Density 0.001%

    No Known Activations