© 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. 37596
    Prev
    Next
    INDEX
    Explanations

    date of birth

    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
    perial
    -0.09
     Ambas
    -0.08
    éĿ¶
    -0.07
    两èĢħ
    -0.07
    _lengths
    -0.07
     rdr
    -0.07
    oule
    -0.07
    strings
    -0.07
    èĩªè¨Ģ
    -0.07
     palestra
    -0.07
    POSITIVE LOGITS
    çİ¥
    0.08
    agem
    0.07
    çļĦåĢ¼
    0.07
    æīĢåľ¨
    0.07
     Unik
    0.07
    é«ĺä½į
    0.07
    ä½İä½į
    0.07
    æĽľ
    0.06
    èĢĢ
    0.06
    æѦæĺĮ
    0.06
    Activations Density 0.003%

    No Known Activations