© 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. 34030
    Prev
    Next
    INDEX
    Explanations

    path, date, energy, time, weights, activity, current

    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
    à¹ģà¸¥à¸°à¸ľà¸¹à¹ī
    -0.07
    append
    -0.07
    _timing
    -0.07
    keh
    -0.06
     leder
    -0.06
    uas
    -0.06
    dei
    -0.06
    bonne
    -0.06
    /up
    -0.06
    üllen
    -0.06
    POSITIVE LOGITS
    ä¹ĭæľĢ
    0.08
     of
    0.08
     difference
    0.08
     ÑģобÑģÑĤвенно
    0.07
    JNI
    0.07
    oyer
    0.07
    idios
    0.07
    ::~
    0.07
     yg
    0.07
     réellement
    0.07
    Activations Density 0.033%

    No Known Activations