© 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. 13437
    Prev
    Next
    INDEX
    Explanations

    survival contest

    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
    æ¾İæ¹ĥ
    -0.08
    级çļĦ
    -0.07
    pty
    -0.07
    æĦı
    -0.06
    Train
    -0.06
    маÑĤÑĭ
    -0.06
     سÙģر
    -0.06
     slog
    -0.06
    Discover
    -0.06
    èĢķèĢĺ
    -0.06
    POSITIVE LOGITS
     survivor
    0.09
    åŃĺæ´»
    0.09
     surv
    0.09
    æ´»å¾Ĺ
    0.08
     survivors
    0.08
     programm
    0.08
     survives
    0.08
    æ´»
    0.08
    ugi
    0.08
     survival
    0.07
    Activations Density 0.003%

    No Known Activations