© 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. 48096
    Prev
    Next
    INDEX
    Explanations

    survival

    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
    онеÑĢ
    -0.07
    ýt
    -0.07
     extensively
    -0.07
    eroy
    -0.07
    оÑĢÑĥ
    -0.07
    大æľīåı¯ä¸º
    -0.07
    åįģä¹Ŀç«ł
    -0.07
    ä¸ŃåĽ½éĿĴå¹´
    -0.07
    ekl
    -0.07
    .Async
    -0.07
    POSITIVE LOGITS
     survival
    0.14
    çĶŁåŃĺ
    0.14
    çĶŁåŃĺçļĦ
    0.13
     Survival
    0.13
    Surv
    0.12
    æ´»ä¸ĭåİ»
    0.11
     survive
    0.11
    åŃĺæ´»
    0.11
     basic
    0.10
     ìĥĿì¡´
    0.10
    Activations Density 0.092%

    No Known Activations