© 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. 58405
    Prev
    Next
    INDEX
    Explanations

    logging and log files

    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
    /div
    -0.08
    ariant
    -0.06
    å¼Ħ
    -0.06
     Gare
    -0.06
    sembl
    -0.06
    PLIED
    -0.06
    ÑĢам
    -0.06
    ista
    -0.06
    ukat
    -0.06
    -Israel
    -0.06
    POSITIVE LOGITS
    æĹ¥å¿Ĺ
    0.10
    gers
    0.10
    gable
    0.09
    GING
    0.09
    trail
    0.09
    .log
    0.08
    zte
    0.08
    .Log
    0.08
    (Log
    0.08
    umbo
    0.08
    Activations Density 0.117%

    No Known Activations