© 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. 18244
    Prev
    Next
    INDEX
    Explanations

    section, paragraph, subdivision, clause

    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
    åºĶèģĺ
    -0.09
    顺åĪ©çļĦ
    -0.08
    ç»Ŀ
    -0.07
    raj
    -0.07
    ross
    -0.07
    éħĿ
    -0.07
    ä¸įè´¥
    -0.07
    cala
    -0.07
    logs
    -0.07
    丰åİ¿
    -0.07
    POSITIVE LOGITS
    عÙħ
    0.08
    è§Ħå®ļ
    0.07
    éĢĤçĶ¨
    0.07
     subparagraph
    0.07
     paragraph
    0.07
    éģ©çĶ¨
    0.07
    ivu
    0.07
     facult
    0.07
    åIJ«çĿĢ
    0.07
     thereof
    0.07
    Activations Density 0.015%

    No Known Activations