© 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. 15230
    Prev
    Next
    INDEX
    Explanations

    column headers and identifiers

    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
    esn
    -0.08
    οÏħÏģγ
    -0.07
    è¦ģçļĦ
    -0.07
    èĩªè¾¾
    -0.07
    ItemAt
    -0.07
    æľĿ天
    -0.07
    UTO
    -0.07
    åİŁåĪĽæĸĩç«ł
    -0.06
    ä¸įçł´
    -0.06
     fatalError
    -0.06
    POSITIVE LOGITS
    0.07
     tâ
    0.07
    uner
    0.06
    æĤ¨çİ°åľ¨çļĦä½įç½®
    0.06
     Nhu
    0.06
    ##_
    0.06
    ед
    0.06
    ÈĻi
    0.06
    ìĩĦ
    0.06
    çĿĢçľ¼
    0.06
    Activations Density 0.013%

    No Known Activations