© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44789
    Prev
    Next
    INDEX
    Explanations

    UNIX operating systems

    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
    е
    -0.17
    å¤ļãģĦ
    -0.15
    à¥ĩ
    -0.13
    ting
    -0.13
    å¤ļãģĦãģ§ãģĻ
    -0.13
    ially
    -0.13
    áĢ·
    -0.12
    ing
    -0.12
    ystal
    -0.12
    sver
    -0.12
    POSITIVE LOGITS
    о
    0.22
    o
    0.21
    gregate
    0.13
    ìį¨
    0.12
    enticated
    0.12
    ighbors
    0.12
    ת
    0.12
    erve
    0.11
    à§įà¦Ł
    0.11
    ÙĦ
    0.11
    Activations Density 5.059%

    No Known Activations