© 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. 64582
    Prev
    Next
    INDEX
    Explanations

    process and procedure

    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
    indsight
    -0.07
    æİĪæĿĥèĮĥåĽ´åĨħ使çĶ¨
    -0.07
     rebound
    -0.07
    SqlServer
    -0.07
    æı´
    -0.07
    ç»ıèIJ¥é£İéĻ©
    -0.07
     arro
    -0.07
     dominante
    -0.07
     assignable
    -0.06
    nows
    -0.06
    POSITIVE LOGITS
    æµģç¨ĭ
    0.18
    æµģç¨ĭåĴĮ
    0.17
     process
    0.17
     procedure
    0.16
    è¿Ļ个è¿ĩç¨ĭ
    0.16
    process
    0.15
     processo
    0.15
    è¿ĩç¨ĭ
    0.15
     procedures
    0.15
    çļĦæµģç¨ĭ
    0.15
    Activations Density 0.318%

    No Known Activations