© 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. 10234
    Prev
    Next
    INDEX
    Explanations

    function definitions

    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
    ((-
    -0.07
     moduleName
    -0.07
    Ī
    -0.07
    awa
    -0.07
    lean
    -0.07
    ¬ģ
    -0.06
    çļĭ
    -0.06
    aud
    -0.06
    aus
    -0.06
    incinn
    -0.06
    POSITIVE LOGITS
     _(
    0.09
     ==(
    0.08
    *)(
    0.08
     abbast
    0.08
    人æĦı
    0.08
     Äijặn
    0.07
    initely
    0.07
    zelf
    0.07
    纾
    0.07
    quiera
    0.07
    Activations Density 0.057%

    No Known Activations