© 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. 56685
    Prev
    Next
    INDEX
    Explanations

    reduce environmental

    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
    æĮĸæİĺåħ¬åı¸
    -0.08
    ÏĦιά
    -0.08
    celet
    -0.07
    磶
    -0.07
    åIJįåī¯åħ¶å®ŀçļĦ
    -0.07
    asm
    -0.07
    åľŁå£¤ä¸Ń
    -0.07
    -sn
    -0.07
     unik
    -0.07
    æĬĬæı¡ä½ı
    -0.07
    POSITIVE LOGITS
    ä¿¡æģ¯çŃī
    0.09
    æľįåĬ¡çŃī
    0.08
    æľºçŃī
    0.08
    人æĪĸ
    0.07
    åĽ¾çŃī
    0.07
    å·¥ç¨ĭçŃī
    0.07
    æ´»åĬ¨çŃī
    0.07
    管çIJĨçŃī
    0.07
    æĬĢæľ¯çŃī
    0.07
    æĢ§æĪĸ
    0.07
    Activations Density 0.148%

    No Known Activations