© 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. 64461
    Prev
    Next
    INDEX
    Explanations

    function calls with parentheses

    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
    ENU
    -0.08
     оÑĤо
    -0.07
    ENO
    -0.07
    iché
    -0.07
    å¤ªè¿ľ
    -0.07
    utora
    -0.07
    rox
    -0.07
    ewan
    -0.07
     pano
    -0.07
    æºĸ
    -0.07
    POSITIVE LOGITS
    auc
    0.07
    ifiable
    0.06
    amma
    0.06
    gerufen
    0.06
    /layouts
    0.06
    åĸľ
    0.06
    æij©
    0.06
     Pr
    0.06
    iti
    0.06
    åľ°ä¸Ĭ
    0.06
    Activations Density 0.405%

    No Known Activations