© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10768
    Prev
    Next
    INDEX
    Explanations

    dice rolls and probability

    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
    天éªĦ
    -0.08
    çīº
    -0.07
    æıIJçIJ´
    -0.07
     formal
    -0.07
    è¾¾åħĭ
    -0.07
    engo
    -0.07
    头çļ®
    -0.07
     Klan
    -0.07
    agas
    -0.07
     Formal
    -0.07
    POSITIVE LOGITS
    æİ·
    0.09
     probability
    0.09
    æ¦Ĥçİĩ
    0.09
     dice
    0.08
    probability
    0.08
     Probability
    0.08
    Probability
    0.08
     probabilities
    0.08
    _probability
    0.07
     unlucky
    0.07
    Activations Density 0.015%

    No Known Activations