© 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. 52014
    Prev
    Next
    INDEX
    Explanations

    biographies and descriptions

    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
    ehend
    -0.07
     these
    -0.06
    ä¹Łåı¯èĥ½æĺ¯
    -0.06
    è¿ĻäºĽä¿¡æģ¯
    -0.06
    ìľłìĿĺ
    -0.06
    isons
    -0.06
    these
    -0.06
    ÑįнеÑĢ
    -0.06
     pb
    -0.06
    æĭŁè®¢
    -0.06
    POSITIVE LOGITS
    éĻĪå¿Ĺ
    0.10
    ütz
    0.07
    ØŃا
    0.07
    ión
    0.07
    uez
    0.07
    phu
    0.07
    é¦ĸåħĪè¦ģ
    0.07
    æĺŁ
    0.07
    ä¾ĭ
    0.07
    æł¹æį®åĽ½å®¶
    0.07
    Activations Density 0.125%

    No Known Activations