© 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. 45201
    Prev
    Next
    INDEX
    Explanations

    .min.js"

    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
    labs
    -0.08
    å¹´èıľ
    -0.08
    emoc
    -0.08
    DAQ
    -0.08
    usine
    -0.08
    вига
    -0.08
    otá
    -0.07
    西çľģ
    -0.07
    åľ¨å¹³æŶ
    -0.07
    éĢļçŁ¥æĪij
    -0.07
    POSITIVE LOGITS
    ialis
    0.07
    aken
    0.07
    arg
    0.06
    ients
    0.06
     preceded
    0.06
    ниÑĨ
    0.06
    roken
    0.06
    rench
    0.06
    a
    0.06
     ver
    0.06
    Activations Density 0.019%

    No Known Activations