© 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. 40806
    Prev
    Next
    INDEX
    Explanations

    function declarations

    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
    iors
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    /cop
    -0.08
    ventory
    -0.08
    ativity
    -0.08
    utherford
    -0.07
    idou
    -0.07
    rlen
    -0.07
    astia
    -0.07
    ostal
    -0.07
    POSITIVE LOGITS
    èį¡èį¡
    0.10
     WINAPI
    0.08
    енÑĮ
    0.08
    ened
    0.08
    ×ķ
    0.08
    sburg
    0.08
    ãģªãģĮãĤī
    0.07
    tä
    0.07
    ÑĦÑĥ
    0.07
    ikuti
    0.07
    Activations Density 0.024%

    No Known Activations