© 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. 25744
    Prev
    Next
    INDEX
    Explanations

    like

    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
    icum
    -0.08
    ç»´ä¿®æľįåĬ¡
    -0.07
    ä¹°åįķ
    -0.07
    åħ¨éĿ¢å®ŀæĸ½
    -0.07
    teo
    -0.07
    Å¡t
    -0.07
     Aufl
    -0.07
     manis
    -0.07
    _PI
    -0.07
    /fw
    -0.07
    POSITIVE LOGITS
    ä¸įåIJĮçļĦæĺ¯
    0.09
    ä¸Ģæł·çļĦ
    0.09
    ä½Ĩä¹Łæľī
    0.08
    ÑģÑĤил
    0.07
    ä¸Ģæł·
    0.07
    åıªä¸įè¿ĩ
    0.07
    ä¹Łåĥı
    0.07
    -sama
    0.07
    éĤ£æł·çļĦ
    0.07
    wen
    0.07
    Activations Density 0.213%

    No Known Activations