© 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. 49683
    Prev
    Next
    INDEX
    Explanations

    St. Johnny Beyond The

    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
    è¿Ļæĺ¯ä¸Ģç§į
    -0.08
    enario
    -0.07
    è¿Ļåľ¨
    -0.07
    apper
    -0.07
    orias
    -0.07
    è¿Ļæĺ¯å¯¹
    -0.07
    åĨįä¸ī
    -0.07
    é¦Ī
    -0.07
    èĩ´çļĦ
    -0.07
    ograma
    -0.07
    POSITIVE LOGITS
    æľīåIJį
    0.07
    深水
    0.07
     ÑĦакÑĤ
    0.07
    istin
    0.07
    мое
    0.06
    çĥĤ
    0.06
    stan
    0.06
    :x
    0.06
    миÑĢ
    0.06
    мами
    0.06
    Activations Density 0.474%

    No Known Activations