© 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. 45762
    Prev
    Next
    INDEX
    Explanations

    depth-first search traversal

    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
    è¿İ
    -0.07
    éľĩåĬ¨
    -0.07
    iasco
    -0.07
    à´±àµĨ
    -0.07
    niÄĻ
    -0.06
    æľĢé«ĺåı¯
    -0.06
    มà¹īา
    -0.06
    å·į
    -0.06
    nable
    -0.06
     Injury
    -0.06
    POSITIVE LOGITS
    otos
    0.08
    çħľ
    0.08
    太åIJİ
    0.07
     молоде
    0.07
    rees
    0.07
    à¸ŀั
    0.07
    yak
    0.07
    ãĥªãĥ¼ãĤ¹
    0.07
    askan
    0.07
    Suffix
    0.06
    Activations Density 0.001%

    No Known Activations