© 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. 61055
    Prev
    Next
    INDEX
    Explanations

    lists, arrays, collections

    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
    åĹ£
    -0.07
    DOI
    -0.06
    ç²
    -0.06
    IEWS
    -0.06
     impuls
    -0.06
    ä¸įä¼ij
    -0.06
     بعدÙĩ
    -0.06
    åħĪéĶĭ
    -0.06
    othi
    -0.06
    parsed
    -0.06
    POSITIVE LOGITS
    мон
    0.08
    hier
    0.07
    agung
    0.07
    кок
    0.07
    okes
    0.07
    æݧèĤ¡éĽĨåĽ¢æľīéĻIJåħ¬åı¸
    0.07
    ÏĮν
    0.07
    计
    0.07
    ért
    0.07
    datum
    0.07
    Activations Density 0.079%

    No Known Activations