© 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. 47707
    Prev
    Next
    INDEX
    Explanations

    code includes .exc, .conf, [index

    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
    -com
    -0.07
    OLA
    -0.06
    chs
    -0.06
    åĸĿå®Į
    -0.06
    å§Ĩæĸ¯
    -0.06
    鼼
    -0.06
    æ¬łæ¬¾
    -0.06
    ÄĥrÄĥ
    -0.06
    éģĹçķĻ
    -0.06
    back
    -0.06
    POSITIVE LOGITS
    utas
    0.08
    å®Ŀåīij
    0.08
    hci
    0.07
    .exc
    0.07
    [Index
    0.07
     congi
    0.07
    configure
    0.07
    ignum
    0.07
     [("
    0.07
    è¡Ģèī²
    0.07
    Activations Density 0.002%

    No Known Activations