© 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. 50841
    Prev
    Next
    INDEX
    Explanations

    exit following certain 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
    ä¸įåłª
    -0.07
    ä½İåIJ¸
    -0.07
    bay
    -0.07
    ä¸Ģè¯ķ
    -0.07
    imenta
    -0.07
     ach
    -0.07
    æľīåı²
    -0.07
    apeut
    -0.07
    /classes
    -0.07
     peter
    -0.07
    POSITIVE LOGITS
    ç¥ī
    0.07
    -shopping
    0.07
    utes
    0.06
    ož
    0.06
     Thi
    0.06
    尾巴
    0.06
    ì²ĺ
    0.06
    æ¸Ń
    0.06
    é¢Ĭ
    0.06
    VV
    0.06
    Activations Density 0.003%

    No Known Activations