© 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. 15694
    Prev
    Next
    INDEX
    Explanations

    struct definition, class, interface, or variable declaration

    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
    æĪĸèĢħæĺ¯
    -0.08
    anel
    -0.07
    éĢļè¿ĩè¿Ļ个
    -0.07
    знÑı
    -0.07
     Nez
    -0.07
     Nack
    -0.07
    queo
    -0.07
    ש×ķ
    -0.07
     filetype
    -0.07
    å§Ĩæĸ¯
    -0.07
    POSITIVE LOGITS
     bowiem
    0.10
     infatti
    0.08
     ugyanis
    0.08
    çĪ±æĺ¯
    0.08
     ведÑĮ
    0.07
    è¿ľä¸ľ
    0.07
    à¹Ģรามี
    0.07
    aed
    0.06
     tardi
    0.06
     totiž
    0.06
    Activations Density 0.061%

    No Known Activations