© 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. 696
    Prev
    Next
    INDEX
    Explanations

    information collection and amount

    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
    追赶
    -0.07
     Ùħجدد
    -0.07
    heck
    -0.07
    è¡Ķ
    -0.07
    .sendMessage
    -0.07
     videoc
    -0.07
    Messaging
    -0.07
     indé
    -0.07
    .executor
    -0.06
     ìĿ´ë¦ĦìĿĦ
    -0.06
    POSITIVE LOGITS
     information
    0.16
     data
    0.15
    è¿ĻäºĽæķ°æį®
    0.14
    è¿ĻäºĽä¿¡æģ¯
    0.14
    ä¿¡æģ¯
    0.14
    information
    0.13
    ä¿¡æģ¯çļĦ
    0.13
    æķ°æį®
    0.13
    à¸Ĥà¹īà¸Ńมูล
    0.12
    -data
    0.12
    Activations Density 0.265%

    No Known Activations