© 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. 37567
    Prev
    Next
    INDEX
    Explanations

    programming context

    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
    綴
    -0.07
    çľº
    -0.07
    peen
    -0.07
    stens
    -0.07
    èİ
    -0.06
    pytest
    -0.06
    éĺ
    -0.06
    èī¶
    -0.06
    REP
    -0.06
    ıs
    -0.06
    POSITIVE LOGITS
    пÑĤи
    0.07
    æĩ¿
    0.07
    è¿ĺæľīçĿĢ
    0.07
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
    èIJ¨æĭī
    0.06
    ẢNG
    0.06
    .hm
    0.06
     Norges
    0.06
    ÙĪØ·
    0.06
     lief
    0.06
    Activations Density 0.005%

    No Known Activations