© 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. 34685
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    æĻ®éĢļ
    -0.07
    abet
    -0.06
    _typ
    -0.06
     Parma
    -0.06
    ಥ
    -0.06
     Milan
    -0.06
    à´¥
    -0.06
    åĪĿå¿ĥèĢħ
    -0.06
    ÂŃt
    -0.06
     habis
    -0.06
    POSITIVE LOGITS
     via
    0.08
    æĹ©æĻļ
    0.08
    iato
    0.07
    山路
    0.07
    è¿Ļ份
    0.07
    æĿ¥èĩª
    0.07
    ä¾Ĩèĩª
    0.07
    via
    0.07
    äºĨè¿ij
    0.06
    elar
    0.06
    Activations Density 0.397%

    No Known Activations