© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22882
    Prev
    Next
    INDEX
    Explanations

    listing items after 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
    ç§į
    -0.07
    ç«£
    -0.07
    åĽŀè¿ĩ头
    -0.06
    笳
    -0.06
    åĽŀ头çľĭ
    -0.06
    è¿Ļæīį
    -0.06
    æİ¥æĽ¿
    -0.06
    é¡Į
    -0.06
     appetite
    -0.06
    anh
    -0.06
    POSITIVE LOGITS
    临éŨ
    0.08
    zada
    0.08
    æ¿Ģåĭµ
    0.07
    å®ŀå¤Ħ
    0.07
    china
    0.07
    æľĿå¤ķ
    0.07
    TestMethod
    0.07
    æīĢ欲
    0.07
    ucci
    0.07
     пÑĢого
    0.07
    Activations Density 0.111%

    No Known Activations