© 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. 40339
    Prev
    Next
    INDEX
    Explanations

    code property definitions

    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
    onn
    -0.08
    onti
    -0.07
    esson
    -0.06
    legs
    -0.06
    eds
    -0.06
    ham
    -0.06
    striction
    -0.06
    fore
    -0.06
    ä¸ĵçĶ¨
    -0.06
    DED
    -0.06
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.09
    åIJĦç§įåIJĦæł·
    0.08
    Įĵ
    0.08
    emachine
    0.08
    .Companion
    0.08
    éĺ¿æĭī伯
    0.08
    lite
    0.08
    弩
    0.07
    åIJĦç§įåIJĦæł·çļĦ
    0.07
    äºĭåįĬåĬŁåĢį
    0.07
    Activations Density 0.014%

    No Known Activations