© 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. 7264
    Prev
    Next
    INDEX
    Explanations

    devices and equipment

    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
    Not in Any Lists

    No Comments

    Negative Logits
    寸
    -0.08
    osa
    -0.08
    åľ¨ç½ijç«Ļ
    -0.07
    åķĥ
    -0.07
    åľ¨çĽ®
    -0.07
    æĹłå¿Į
    -0.06
    æ¨Ł
    -0.06
    .toInt
    -0.06
    cor
    -0.06
    åĴĮè¦ģæ±Ĥ
    -0.06
    POSITIVE LOGITS
    çļĦå·¥ä½ľåİŁçIJĨ
    0.11
    å·¥ä½ľåİŁçIJĨ
    0.10
    éĽıå½¢
    0.09
    åİŁçIJĨ
    0.09
    鼼
    0.08
     malfunction
    0.08
     prototype
    0.08
    å¼ıçļĦ
    0.08
    -like
    0.08
    çŃī设å¤ĩ
    0.08
    Activations Density 0.190%

    No Known Activations