© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14350
    Prev
    Next
    INDEX
    Explanations

    court dates and case filings

    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
    atre
    -0.07
     specific
    -0.07
     default
    -0.06
     suff
    -0.06
    ÑĬ
    -0.06
    dür
    -0.06
     t
    -0.06
     [
    -0.06
    [U
    -0.06
    èݽ
    -0.06
    POSITIVE LOGITS
    yme
    0.09
    igm
    0.08
    rome
    0.08
    ยà¹Į
    0.08
    rafa
    0.08
    ÛĮÙħÛĮ
    0.08
    igre
    0.07
    []}
    0.07
    ัà¸ĩ
    0.07
    игÑĢа
    0.07
    Activations Density 0.170%

    No Known Activations