© 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. 7199
    Prev
    Next
    INDEX
    Explanations

    geographic divisions or administrative units

    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
     mut
    -0.08
    iern
    -0.07
    æ¨ĭ
    -0.07
     priz
    -0.06
    SCII
    -0.06
    åºŀ大
    -0.06
    athy
    -0.06
    WithTitle
    -0.06
     camps
    -0.06
     ass
    -0.06
    POSITIVE LOGITS
    éļ¶å±ŀäºİ
    0.12
    æīĢåľ¨çļĦ
    0.11
     dentro
    0.11
     within
    0.11
    ä¹ĥèĩ³
    0.10
     ضÙħÙĨ
    0.10
    æīĢåľ¨
    0.10
    within
    0.10
     innerhalb
    0.09
    _within
    0.09
    Activations Density 0.855%

    No Known Activations