© 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. 13237
    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
    çļĦåIJĮ
    -0.05
    Q
    -0.05
    åĦ¿çļĦ
    -0.05
    为çİĭ
    -0.05
    ua
    -0.05
    ¨
    -0.05
    æľ
    -0.05
    åĦ¿
    -0.05
    为åħ¶
    -0.05
    era
    -0.05
    POSITIVE LOGITS
    å¸ĮæľĽèĩªå·±
    0.10
    æİĸ
    0.09
     gezi
    0.08
    oppi
    0.08
    kens
    0.08
    ç¥ŀé¾Ļ
    0.08
    eated
    0.08
    ByExample
    0.08
    ataka
    0.08
    çĿĢèĩªå·±
    0.07
    Activations Density 0.001%

    No Known Activations