© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38793
    Prev
    Next
    INDEX
    Explanations

    chapter number or title

    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
    ä¸įæģ¯
    -0.07
    éĶĻ误æĪĸ
    -0.07
    atable
    -0.07
    æĬĸåĬ¨
    -0.06
    æŃ¤é¡¹
    -0.06
    å¿ĺè¿Ķ
    -0.06
    /documentation
    -0.06
    çĶŁæ°´
    -0.06
     aggregated
    -0.06
     similarly
    -0.06
    POSITIVE LOGITS
    çķªå¤ĸ
    0.10
    è¿Ľä¸ĢæŃ¥çļĦ
    0.08
    æŁ¥çľĭåħ¨æĸĩ
    0.08
    ipc
    0.08
    ãģ¨ãģ¯ãģĦãģĪ
    0.08
    neys
    0.07
    å¾ħç»Ń
    0.07
    æİ¥ä¸ĭæĿ¥çļĦ
    0.07
     POV
    0.07
    åįģåĽĽç«ł
    0.07
    Activations Density 0.168%

    No Known Activations