© 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. 47299
    Prev
    Next
    INDEX
    Explanations

    word usage and linguistics

    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
    年建éĢł
    -0.08
    åı£å¾Ħ
    -0.08
    ibal
    -0.07
    æĺĤ
    -0.07
    à¹Ĥล
    -0.07
    -events
    -0.07
    æ¯ıåIJį
    -0.07
    -sdk
    -0.07
    odom
    -0.07
    ä¸Ĭä¸ĭ游
    -0.07
    POSITIVE LOGITS
     gramm
    0.10
     linguistic
    0.10
     lexical
    0.10
     lingu
    0.09
     Lingu
    0.09
    æ¯įè¯Ń
    0.08
     stylist
    0.08
     corpus
    0.08
     Word
    0.08
     usage
    0.08
    Activations Density 0.122%

    No Known Activations