© 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. 45749
    Prev
    Next
    INDEX
    Explanations

    qualities and benefits

    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
      ↵↵
    -0.07
    åı°
    -0.07
    ô
    -0.07
    ï¼Ī
    -0.07
      ↵
    -0.07
     (
    -0.07
     tightly
    -0.06
    /svg
    -0.06
       ↵↵
    -0.06
    ç»Ħç»ĩ
    -0.06
    POSITIVE LOGITS
    åıĺå¾ĹæĽ´åĬł
    0.09
    ä¸įæĿ¥
    0.09
    缸åħ³æݨèįIJ
    0.08
    ä»¥æĽ´åĬł
    0.08
    éĵĿä¸ļ
    0.08
    æľ¬æĸĩ为
    0.08
    ÙģÙĪ
    0.08
    æľīäºĨæĽ´
    0.08
    åIJĦ个æĸ¹éĿ¢
    0.08
    带æĿ¥æĽ´å¤ļ
    0.08
    Activations Density 0.007%

    No Known Activations