© 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. 3146
    Prev
    Next
    INDEX
    Explanations

    vendors or projects

    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
    legend
    -0.07
    ÂŃs
    -0.07
    hest
    -0.07
    æĸ¹
    -0.07
    arma
    -0.07
    åĴĮä»ĸ
    -0.07
    leve
    -0.06
    esp
    -0.06
    ä»°
    -0.06
    æĿĢ人
    -0.06
    POSITIVE LOGITS
    ç»ĵè¯Ń
    0.07
    Ùijا
    0.07
    åľ°å¼Ģå±ķ
    0.07
    enburg
    0.07
    åĺ¿
    0.07
    åĸµ
    0.07
    idu
    0.07
    å´Ĺ
    0.07
    çļĦæľªæĿ¥
    0.07
    第åįģäºĮç«ł
    0.07
    Activations Density 0.008%

    No Known Activations