© 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. 44099
    Prev
    Next
    INDEX
    Explanations

    rightwheel or logging messages

    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
    à¸ŀาà¸Ļ
    -0.07
    eping
    -0.07
     kep
    -0.07
     cortes
    -0.07
    közi
    -0.07
    èĴ²
    -0.07
    ä»ĺ
    -0.07
    earn
    -0.07
    ART
    -0.07
    Compact
    -0.07
    POSITIVE LOGITS
    piler
    0.07
    _ABI
    0.07
    0.07
    lobber
    0.07
    делÑĮник
    0.07
    .backend
    0.06
    æ´»å¾Ĺ
    0.06
    оÑħÑĢа
    0.06
    halt
    0.06
     Wolver
    0.06
    Activations Density 0.146%

    No Known Activations