© 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. 13524
    Prev
    Next
    INDEX
    Explanations

    competition stages

    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
    ¾
    -0.08
    intis
    -0.08
    worth
    -0.07
    ÅĤugi
    -0.07
    å¤ĸäºĭ
    -0.07
    äºĮåįģ大
    -0.07
    orea
    -0.07
    sburg
    -0.07
    usen
    -0.07
    åħ³äºİåģļ好
    -0.07
    POSITIVE LOGITS
    ä¸Ĭ马
    0.07
    å¾·åĭĴ
    0.06
     Hof
    0.06
    ina
    0.06
    Locker
    0.06
    [assembly
    0.06
    ä¸Ńæŀ¢
    0.06
    ä¸½å¨ľ
    0.06
    æŃ¤èµ·å½¼ä¼ı
    0.06
    ÙĦØ©
    0.06
    Activations Density 0.003%

    No Known Activations