© 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. 23923
    Prev
    Next
    INDEX
    Explanations

    certainty and prediction

    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
    èĻļå¿ĥ
    -0.07
    ini
    -0.07
    ÙİÙijÙī
    -0.07
    INI
    -0.07
    OrUpdate
    -0.07
    اÙĦØŃØ©
    -0.07
    åħ¼
    -0.07
    aps
    -0.07
    atories
    -0.07
    å¦ĸåħ½
    -0.07
    POSITIVE LOGITS
     certainty
    0.12
    ç¡®å®ļæĢ§
    0.12
     certeza
    0.11
     guaranteed
    0.10
     Cert
    0.10
     guarantee
    0.10
    åı¯ä»¥ä¿Ŀè¯ģ
    0.09
     chắc
    0.09
    ainty
    0.09
     sure
    0.09
    Activations Density 0.047%

    No Known Activations