© 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. 47963
    Prev
    Next
    INDEX
    Explanations

    coin, dice, and randomness

    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
    åĬłçıŃåĬłçĤ¹
    -0.08
    ifique
    -0.08
    icat
    -0.07
     removable
    -0.07
    æģįçĦ¶å¤§æĤŁ
    -0.07
    поÑĢ
    -0.07
    rios
    -0.07
    igente
    -0.07
    çł´
    -0.07
     Craw
    -0.07
    POSITIVE LOGITS
     probabil
    0.10
    æİ·
    0.09
     tossing
    0.09
    ä¸Ģ次çļĦ
    0.09
    éļıæľº
    0.09
     randomness
    0.08
    andom
    0.08
    สุ
    0.08
     outcome
    0.08
     tossed
    0.08
    Activations Density 0.013%

    No Known Activations