© 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. 13113
    Prev
    Next
    INDEX
    Explanations

    grant numbers and patent IDs

    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
    éĩij马
    -0.08
    engg
    -0.08
    èµĦ讯ä¸Ńå¿ĥ
    -0.07
    UND
    -0.07
    ersch
    -0.07
     dela
    -0.07
    menta
    -0.07
    æ·±åIJ¸
    -0.07
    ä½ľä¸ºä¸Ģ家
    -0.07
    çº¢é¢ľ
    -0.07
    POSITIVE LOGITS
    è
    0.08
    ounces
    0.07
    sez
    0.07
    nbsp
    0.06
    ocs
    0.06
    马å°Ķ
    0.06
    loe
    0.06
    èĢģè¡Ĺ
    0.06
    bbing
    0.06
    enseur
    0.06
    Activations Density 0.048%

    No Known Activations