© 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. 7676
    Prev
    Next
    INDEX
    Explanations

    Chinese phrases

    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®ĥå°±æĺ¯
    -0.08
    辺
    -0.08
    flater
    -0.08
    å®ĥåĢij
    -0.07
    ä½Ĩå®ĥ们
    -0.07
    å®ĥéĤ£
    -0.07
    udas
    -0.07
    èµıå¿ĥæĤ¦
    -0.07
    ç¸ģ
    -0.07
    ryn
    -0.07
    POSITIVE LOGITS
    对ä¸Ĭè¿°
    0.08
    åľ¨ä¸Ĭè¿°
    0.07
    ä¸Ķä¸į
    0.07
    æĥħåĨµåĪĨæŀIJ
    0.07
    并å¸ĮæľĽ
    0.07
    ä¸Ķ
    0.07
    麸
    0.06
    åĪ°è¿Ļ个
    0.06
    pbs
    0.06
    并已
    0.06
    Activations Density 0.017%

    No Known Activations