© 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. 16700
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
     lug
    -0.07
    oun
    -0.07
    anj
    -0.07
    idis
    -0.07
    oud
    -0.07
    rol
    -0.06
    第ä¸Ģ人æ°ijåĮ»éĻ¢
    -0.06
     ^=
    -0.06
    èĢ»
    -0.06
    åįĹå®ĭ
    -0.06
    POSITIVE LOGITS
    lint
    0.07
    ilÃł
    0.07
    æĪIJå¥Ĺ
    0.07
    ä¹ĥèĩ³
    0.07
    åĪ©åĻ¨
    0.07
    asaran
    0.07
    åĵªäºĽ
    0.07
    ownie
    0.07
    cez
    0.07
    _marshall
    0.07
    Activations Density 0.005%

    No Known Activations