© 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. 56025
    Prev
    Next
    INDEX
    Explanations

    consecutive discourse connectors

    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
    imore
    -0.08
    orsch
    -0.08
    Sibling
    -0.08
    顾åIJįæĢĿ
    -0.08
    ä¸ĭåIJĮ
    -0.08
    ustos
    -0.08
    örd
    -0.08
     à¸ķามระà¸Ķัà¸ļ
    -0.08
    orman
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.07
    POSITIVE LOGITS
    SMART
    0.06
    åĴ¯
    0.06
    ä»Ĭ天å°ıç¼ĸå°±
    0.06
    åĴ§
    0.06
     воÑĤ
    0.06
    ķ
    0.06
    mene
    0.06
    enda
    0.06
    avis
    0.06
    "M
    0.06
    Activations Density 0.009%

    No Known Activations