© 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. 45905
    Prev
    Next
    INDEX
    Explanations

    confidence 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
    驼
    -0.08
     stri
    -0.07
    amics
    -0.07
    Äįer
    -0.07
    áce
    -0.07
    HEET
    -0.07
    ç³ľ
    -0.07
    pson
    -0.06
     moon
    -0.06
    çIJ¼æĸ¯
    -0.06
    POSITIVE LOGITS
     confidence
    0.10
    置信
    0.09
     Confidence
    0.09
    credible
    0.09
     credible
    0.08
    ä¸İç»´ä¿®
    0.08
    confidence
    0.08
    ança
    0.07
     probability
    0.07
     percentile
    0.07
    Activations Density 0.008%

    No Known Activations