© 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. 41134
    Prev
    Next
    INDEX
    Explanations

    parentheses and math expressions

    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
    å°±æĺ¯è¦ģ
    -0.07
    ftype
    -0.07
    ä¸ĭåIJĮ
    -0.07
     sourceMappingURL
    -0.06
     Conheça
    -0.06
     {}".
    -0.06
    ëĵ¯
    -0.06
    uet
    -0.06
     *))
    -0.06
    çļĦ大好
    -0.06
    POSITIVE LOGITS
    è¿Ļæł·ä¸Ģç§į
    0.09
    lesia
    0.09
     ugyanis
    0.08
    reja
    0.08
    è¿Ŀåıįä¸Ĭè¿°
    0.07
    ä»Ģä¹Īåij¢
    0.07
    è¿Ļæł·çļĦä¸Ģ个
    0.07
    ãĢģãĢĮ
    0.07
     firstly
    0.07
    ((((
    0.07
    Activations Density 0.087%

    No Known Activations