© 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. 29270
    Prev
    Next
    INDEX
    Explanations

    survival and death rates

    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
     improvis
    -0.06
     rim
    -0.06
     ferment
    -0.06
    æīģ
    -0.06
    ÑīÑĸ
    -0.06
    æĺ¨å¤ľ
    -0.06
     pilota
    -0.06
    èİ·èµŀ
    -0.06
    æĺ¥æĦı
    -0.06
    åħ¥å¾®
    -0.06
    POSITIVE LOGITS
    ä¸įæŃ»
    0.10
    æŃ»äº¡
    0.10
    æŃ»äº¡çļĦ
    0.10
    death
    0.10
     mortality
    0.09
     death
    0.09
    åİ»ä¸ĸ
    0.09
    Death
    0.09
    å¢ĵç¢ij
    0.09
    æŃ»äº¡çİĩ
    0.09
    Activations Density 0.118%

    No Known Activations