© 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. 43808
    Prev
    Next
    INDEX
    Explanations

    probability calculations

    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
    å¼łå¤§
    -0.06
     cod
    -0.06
    çļĦä¸Ģå¼ł
    -0.06
    æĮĿ
    -0.06
     layers
    -0.06
     absolute
    -0.06
    velle
    -0.06
    uelas
    -0.06
     gros
    -0.06
    å¸ĺ
    -0.06
    POSITIVE LOGITS
    æ¦Ĥçİĩ
    0.08
    åĩij
    0.08
    MESS
    0.08
    engi
    0.07
     probabilities
    0.07
    èĩ³æѤ
    0.07
     probability
    0.07
    åįĬåĪĨ
    0.07
    omo
    0.07
     Probability
    0.07
    Activations Density 0.001%

    No Known Activations