© 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. 62563
    Prev
    Next
    INDEX
    Explanations

    medical or technical equipment components

    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
    å¤ļä¸Ģ份
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    æĭĽ
    -0.07
    ä»ĬåIJİçļĦ
    -0.07
    åľ¨ä»ĬåIJİçļĦ
    -0.07
    ä¸įè¦ģåľ¨
    -0.07
    åħ³äºİè¿Ľä¸ĢæŃ¥
    -0.07
     пÑĭ
    -0.07
    åľ¨æŃ¤æ¬¡
    -0.07
    ä¸įæİĴéĻ¤
    -0.07
    POSITIVE LOGITS
    éĢļ常æĺ¯
    0.13
    éĢļ常为
    0.11
    ä¸ĢèĪ¬æĺ¯
    0.11
     usually
    0.10
    ä¸ĢèĪ¬éĩĩçĶ¨
    0.10
    usually
    0.10
     typically
    0.10
    ä¸ĢèĪ¬ä¸º
    0.10
    Usually
    0.10
     عادة
    0.09
    Activations Density 0.660%

    No Known Activations