© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21588
    Prev
    Next
    INDEX
    Explanations

    steps and changes over time

    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
    serter
    -0.09
    ispo
    -0.08
    _picker
    -0.08
    å¾ģ稿
    -0.08
    illo
    -0.08
    afari
    -0.08
    çļĦ好æĪIJ绩
    -0.08
    Scanner
    -0.08
    umpang
    -0.08
    ç¦ıåħĭæĸ¯
    -0.08
    POSITIVE LOGITS
     stages
    0.11
    æ¯ıä¸ĢæŃ¥
    0.10
    è¿ĩç¨ĭ
    0.10
    æ¯ıä¸Ģ次
    0.10
    ä¸ĢæŃ¥æŃ¥
    0.09
     successive
    0.09
     step
    0.09
    è¿ĩç¨ĭä¸ŃçļĦ
    0.08
    è¿ĩç¨ĭçļĦ
    0.08
    -stage
    0.08
    Activations Density 0.011%

    No Known Activations