© 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. 34929
    Prev
    Next
    INDEX
    Explanations

    macrolide antibiotics

    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
     Hogan
    -0.08
    éģ½
    -0.07
    åĩĨå¤ĩå·¥ä½ľ
    -0.07
    éħįæĪ´
    -0.07
    uve
    -0.07
    obil
    -0.07
    èģļæ°¨
    -0.07
    setLayout
    -0.07
     menda
    -0.07
    就差
    -0.07
    POSITIVE LOGITS
    ä¸įæĺ¯ä¸ºäºĨ
    0.18
    æĹ¢æĺ¯
    0.17
    çĶ¨ä½ľ
    0.17
    ä¸įä»ħæĺ¯
    0.17
    ä¸įä»ħä»ħæĺ¯
    0.16
    主è¦ģçĶ¨äºİ
    0.14
    ä¸įä»ħåı¯ä»¥
    0.14
    æĹ¢èĥ½
    0.14
    çĶ¨äºİ
    0.13
    ä¸įåıªæĺ¯
    0.13
    Activations Density 0.537%

    No Known Activations