© 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. 4852
    Prev
    Next
    INDEX
    Explanations

    programming code and names

    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
    سÙĬر
    -0.07
    è¯ŀ
    -0.07
    ä¸ĭæīĭ
    -0.07
    .TryParse
    -0.07
    ëĦIJ
    -0.06
    次åħļ代ä¼ļ
    -0.06
    alina
    -0.06
    éħİ
    -0.06
    æĽĿ
    -0.06
    ehme
    -0.06
    POSITIVE LOGITS
    ikin
    0.07
    ikas
    0.07
     Hassan
    0.07
    åĨĽèIJ¥
    0.07
     ÙĪØ¥ÙĦÙī
    0.07
    ç«ĭç§ĭ
    0.06
    æĸ°æĦı
    0.06
    çĤ¹èµŀ
    0.06
     Miz
    0.06
    夷
    0.06
    Activations Density 0.002%

    No Known Activations