© 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. 18054
    Prev
    Next
    INDEX
    Explanations

    proper names and abbreviations

    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
    olt
    -0.09
    tion
    -0.07
    ặt
    -0.07
    pector
    -0.07
    olet
    -0.07
    æľīæĪIJ
    -0.07
    æĽ²
    -0.07
    arden
    -0.07
    ught
    -0.07
    pell
    -0.07
    POSITIVE LOGITS
    èµģ
    0.07
     ÙģرÙĪ
    0.07
    åħ³äºİåĬłå¼º
    0.07
    åĽłä¸ºåľ¨
    0.07
    æĿİçİī
    0.07
    计çļĦ
    0.07
    iloc
    0.06
    зма
    0.06
    ä¸īæĽ´
    0.06
    elize
    0.06
    Activations Density 0.037%

    No Known Activations