© 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. 54920
    Prev
    Next
    INDEX
    Explanations

    mercantile/commodity names

    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
    ãģ¨ãģĦãģĪãģ°
    -0.08
    ↵↵↵↵↵↵↵↵
    -0.08
    ç¼ļ
    -0.07
    issen
    -0.07
     ÙĨÙģسÙĩا
    -0.07
    ãģ¨è¨ĢãģĪãģ°
    -0.07
     itself
    -0.07
    ãĥªãĤ¨
    -0.07
    nier
    -0.07
    kata
    -0.07
    POSITIVE LOGITS
     etc
    0.08
    /etc
    0.07
     Nev
    0.07
    ãģĿãģ®ä»ĸãģ®
    0.07
    çŃīè¿Ľè¡Į
    0.07
    ç±»çŃī
    0.07
    è´¹çŃī
    0.06
     specials
    0.06
    ãģĿãģĹãģ¦
    0.06
     sowie
    0.06
    Activations Density 0.320%

    No Known Activations