© 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. 44774
    Prev
    Next
    INDEX
    Explanations

    face, shoulder, mouth

    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
    ĵĺ
    -0.07
    æ´Ľå¤«
    -0.07
    ãģªãģĬ
    -0.07
    åľ¨å·¥ä½ľä¸Ĭ
    -0.07
    imiter
    -0.07
    ante
    -0.06
    建ç«ĭåľ¨
    -0.06
    åĴĮåĪĽæĸ°
    -0.06
    åħĭå°Ķ
    -0.06
    让èĩªå·±çļĦ
    -0.06
    POSITIVE LOGITS
    åıĬåij¨è¾¹
    0.08
     vicinity
    0.08
    æ¯ıä¸Ģ个è§ĴèIJ½
    0.08
    è¿ĩå¤ľ
    0.08
    ëĭ¤ê°Ģ
    0.07
    theses
    0.07
    ä»Ģä¹Īåľ°æĸ¹
    0.07
    leon
    0.07
    æ´»åĬ¨æŶ
    0.07
     ê°ĢëĵĿ
    0.07
    Activations Density 0.318%

    No Known Activations