© 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. 64931
    Prev
    Next
    INDEX
    Explanations

    names like Yang, Lam, Peng

    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
    æĿ¥æºIJç½ij绾
    -0.08
    é¢ĵ
    -0.08
    -With
    -0.08
    à§ģà¦ķ
    -0.08
    æĭĽæłĩç½ij
    -0.08
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.08
    åĪĺåħĪçĶŁ
    -0.08
    çİĭæ°ı
    -0.08
    }else
    -0.07
    æī§è¡Įç¨ĭåºı
    -0.07
    POSITIVE LOGITS
    çĶŁåľ¨
    0.08
     arg
    0.07
    __
    0.06
    çĶŁäºİ
    0.06
    cks
    0.06
    å®Ļ
    0.06
    arity
    0.06
    梦
    0.06
     born
    0.06
     Gum
    0.06
    Activations Density 0.046%

    No Known Activations