© 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. 58879
    Prev
    Next
    INDEX
    Explanations

    picking sequences from character sets

    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
    çĽ¸ä¼¼æĸĩçĮ®
    -0.08
    (...)
    -0.07
    ourage
    -0.06
    éħİ
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
    æĿ¥å¾Ĺ
    -0.06
    ample
    -0.06
     Haush
    -0.06
    fuck
    -0.06
    μÏĢ
    -0.06
    POSITIVE LOGITS
    hak
    0.07
    ضÙĬ
    0.07
    æĺ¯ä¸Ģæľ¬
    0.07
    ç«ĭæĸ°
    0.07
    æĸ°éĶIJ
    0.07
    貫
    0.07
    uestas
    0.07
    tum
    0.07
    mere
    0.07
    ä¸īå¹´æĿ¥
    0.07
    Activations Density 0.017%

    No Known Activations