© 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. 22253
    Prev
    Next
    INDEX
    Explanations

    principal bundles and extensions

    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
    ä¸īéŨ
    -0.08
    uary
    -0.07
    anth
    -0.07
     anthrop
    -0.07
    æIJģ
    -0.07
    Anth
    -0.07
    رش
    -0.07
    rhs
    -0.07
    è·¨çķĮ
    -0.06
    ä¸İ人
    -0.06
    POSITIVE LOGITS
    maps
    0.09
     stitches
    0.08
    פ×ķת
    0.08
    解å¼Ģ
    0.07
    æĹłçºº
    0.07
    mapping
    0.07
    /master
    0.07
    steder
    0.07
    ç»·
    0.07
    à¸ĭà¹īà¸Ńà¸Ļ
    0.07
    Activations Density 0.005%

    No Known Activations