© 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. 47956
    Prev
    Next
    INDEX
    Explanations

    quality

    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
    aner
    -0.08
    績
    -0.08
    )["
    -0.07
    .cgi
    -0.07
     sounding
    -0.07
    ¾
    -0.07
    elter
    -0.07
    æĸ¯åĿ¦
    -0.07
    eler
    -0.07
    æľ¬æĸĩæĿ¥èĩª
    -0.07
    POSITIVE LOGITS
    eries
    0.07
    PELL
    0.06
    æģĻ
    0.06
    ä¿ĬæĿ°
    0.06
    weeney
    0.06
     باÙĦÙĦÙĩ
    0.06
    ายà¸Ļ
    0.06
    ément
    0.06
    Ãłm
    0.06
    ãs
    0.06
    Activations Density 0.031%

    No Known Activations