© 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. 60472
    Prev
    Next
    INDEX
    Explanations

    probability of 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
     Merry
    -0.07
    rano
    -0.07
    atos
    -0.07
    çļĦ缮çļĦæĺ¯
    -0.07
    ewater
    -0.07
    è²ī
    -0.07
     коем
    -0.07
    磶
    -0.06
    ä¸ĢéĢļ
    -0.06
    unset
    -0.06
    POSITIVE LOGITS
    æ¦Ĥçİĩ
    0.13
    çļĦæ¦Ĥçİĩ
    0.12
     probability
    0.12
    Probability
    0.11
     Probability
    0.11
     probabilities
    0.10
    probability
    0.10
    _probability
    0.09
     ocurr
    0.09
    åıijçĶŁçİĩ
    0.09
    Activations Density 0.012%

    No Known Activations