© 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. 27324
    Prev
    Next
    INDEX
    Explanations

    function call arguments

    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
    pgsql
    -0.08
    postgresql
    -0.08
    次åĽŀ
    -0.08
    ç«£
    -0.08
    conditions
    -0.08
    ollo
    -0.08
     ÐļÑĢаÑģи
    -0.08
    ignano
    -0.07
    amment
    -0.07
    ventory
    -0.07
    POSITIVE LOGITS
    对
    0.07
    ãĤī
    0.07
    ï¼Ī
    0.07
    对æѤ
    0.06
    ss
    0.06
    Z
    0.06
    Ñģ
    0.06
    æĽ¾
    0.06
    æķ¢
    0.06
    _,
    0.06
    Activations Density 0.111%

    No Known Activations