© 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. 40735
    Prev
    Next
    INDEX
    Explanations

    involves activation, necessary typically

    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
    并ä¸Ķè¿ĺ
    -0.07
     übrigens
    -0.07
     zal
    -0.06
     zaten
    -0.06
    зÑĮ
    -0.06
    lobby
    -0.06
    ிர
    -0.06
    erior
    -0.06
    ÙĦÙĪÙĦ
    -0.06
    etail
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩåIJĦç§į
    0.07
    arat
    0.07
    arin
    0.06
    fert
    0.06
    Ľ
    0.06
    çļĦåij½è¿IJ
    0.06
    éĩįè¦ģæĮĩ示
    0.06
    —in
    0.06
    —or
    0.06
    emek
    0.06
    Activations Density 1.161%

    No Known Activations