© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58862
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and functions

    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
    ża
    -0.07
    婪
    -0.07
    azon
    -0.07
    undu
    -0.07
    _FETCH
    -0.07
    åIJ¦
    -0.07
    sud
    -0.07
    _pat
    -0.06
    look
    -0.06
    jaz
    -0.06
    POSITIVE LOGITS
     unknown
    0.07
     predic
    0.07
    å¾IJå¾IJ
    0.07
    æľªçŁ¥
    0.07
    éĻIJæľŁ
    0.07
    æľªçŁ¥çļĦ
    0.07
    ме
    0.07
     Unknown
    0.07
    unknown
    0.07
    åłª
    0.06
    Activations Density 0.008%

    No Known Activations