© 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. 4902
    Prev
    Next
    INDEX
    Explanations

    versus

    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
    inary
    -0.07
    Ñģпа
    -0.07
    æķ´ä½ĵ
    -0.07
    éĻ£
    -0.07
    以èĩ³
    -0.07
    éĺµ
    -0.07
    å²ĽçļĦ
    -0.07
    æķ´ä½ĵä¸Ĭ
    -0.07
    opsis
    -0.07
    idth
    -0.07
    POSITIVE LOGITS
    Å¡tÄĽ
    0.08
    æĭ±
    0.07
    ìŀ¡
    0.07
     scheduled
    0.07
    Throws
    0.07
    çĶŁçī©å·¥ç¨ĭ
    0.07
    ẩu
    0.07
    åĿij
    0.07
    ifikasi
    0.07
    èĴĻ
    0.07
    Activations Density 0.059%

    No Known Activations