© 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. 59113
    Prev
    Next
    INDEX
    Explanations

    creative expression and impact

    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
    æĶ¯éħį
    -0.08
    ä¸Ń段
    -0.07
     filmer
    -0.06
    åħ¨ç¨ĭ
    -0.06
    anyak
    -0.06
    主宰
    -0.06
    æĸ¹æŃ£
    -0.06
     overse
    -0.06
    oho
    -0.06
    å¾ħ
    -0.06
    POSITIVE LOGITS
    åı¯ä»¥èµ·åĪ°
    0.10
     powerful
    0.08
    åĪĽä½ľèĢħ
    0.08
    ä¼łéĢĴ
    0.08
    æĦŁæŁĵåĬĽ
    0.07
    çļĦ表达
    0.07
    æ½ľç§»é»ĺåĮĸ
    0.07
    èĥ½èµ·åĪ°
    0.07
    æĺ¯æľĢ好çļĦ
    0.07
    åħ±é¸£
    0.07
    Activations Density 0.088%

    No Known Activations