© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44434
    Prev
    Next
    INDEX
    Explanations

    paths, affairs, symbols

    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
    Negative Logits
    ,but
    -0.09
    ä½Ĩä¸įè¦ģ
    -0.09
    ä½Ĩ对äºİ
    -0.09
    ãģĿãģĨãģ§ãģĻãģĮ
    -0.09
    ä¸įåıªæĺ¯
    -0.09
    ãģĦãģ¾ãģĹãģŁãģĮ
    -0.09
    ä½Ĩçİ°åľ¨
    -0.09
    ä¸įæĺ¯åľ¨
    -0.09
     übrigens
    -0.08
    ä½Ĩè¿Ļ
    -0.08
    POSITIVE LOGITS
     [&
    0.09
    æīį对
    0.08
     anzi
    0.07
    ãģ®ãģ»ãģĨãģĮ
    0.07
    ãĤĢãģĹãĤį
    0.07
    åıĸèĢĮ代ä¹ĭ
    0.07
    æīįè¡Į
    0.07
    è¿Ļæīįæĺ¯
    0.07
    ãģ®æĸ¹ãģĮ
    0.07
     thereof
    0.07
    Activations Density 0.305%

    No Known Activations