© 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. 44663
    Prev
    Next
    INDEX
    Explanations

    foreign language translations

    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
    åİĭåĻ¨
    -0.08
    æľīç¼ĺ
    -0.08
    ÑĤаж
    -0.07
    Sher
    -0.07
    æѤè¡Į
    -0.07
     odst
    -0.07
    agre
    -0.07
    æľ¬èī²
    -0.07
    edos
    -0.07
    íĮ¨
    -0.07
    POSITIVE LOGITS
    ç¿»è¯ij
    0.11
    çļĦæĦıæĢĿæĺ¯
    0.10
    çļĦæĦıæĢĿ
    0.10
     translates
    0.10
    0.09
    æĦıæĢĿæĺ¯
    0.09
     translated
    0.09
    è¯ijæĸĩ
    0.09
    è¯ij
    0.09
    translated
    0.09
    Activations Density 0.179%

    No Known Activations