© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52038
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    Negative Logits
    wend
    -0.08
    enni
    -0.08
    ulg
    -0.07
    hle
    -0.07
    ettel
    -0.07
    aton
    -0.07
     configFile
    -0.07
    ofer
    -0.07
    ç¯ĵ
    -0.07
    ule
    -0.07
    POSITIVE LOGITS
    ä¸īèĢħ
    0.10
    è¿Ļä¸ī
    0.09
    è¿Ļä¸ī个
    0.08
    ä¸īéĩį
    0.08
    è¿Ļä¸īç§į
    0.07
    ä¸ī大
    0.07
    ä¸īæĸ¹
    0.07
    æ¼Ķ
    0.06
     triple
    0.06
    _NONE
    0.06
    Activations Density 0.357%

    No Known Activations