© 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. 25940
    Prev
    Next
    INDEX
    Explanations

    numbers before parentheses

    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
     séc
    -0.07
    äºĭæĢģ
    -0.07
    ngen
    -0.07
    abbage
    -0.07
    æ´»
    -0.07
    æĸ½
    -0.07
    .backup
    -0.07
    ~-
    -0.07
    è¿ĻäºĽäºĭæĥħ
    -0.07
    _backup
    -0.06
    POSITIVE LOGITS
    عر
    0.07
    orc
    0.07
    è¿·æĥij
    0.07
     desc
    0.07
    çĻ¾åĪĨä¹ĭ
    0.07
    acman
    0.07
    Ut
    0.06
    ä¸ī线
    0.06
    Ai
    0.06
     ÐľÐ¾Ð¹
    0.06
    Activations Density 0.126%

    No Known Activations