© 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. 45683
    Prev
    Next
    INDEX
    Explanations

    chain-only immunoglobulin

    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
    regor
    -0.08
     makin
    -0.07
    æĺ¯ä¸įåı¯èĥ½
    -0.07
    дни
    -0.07
    ä¸Ģæĸĩ
    -0.07
    idler
    -0.07
    ãĥ¬ãĥĥ
    -0.07
    ä¹Łæĺ¯æľĢ
    -0.07
    ).__
    -0.06
    æĹłä»¥
    -0.06
    POSITIVE LOGITS
    æ¯ĶæĻ®éĢļ
    0.21
    ä¸įåIJĮäºİ
    0.18
    instead
    0.15
     unconventional
    0.15
     instead
    0.15
    ä»£æĽ¿
    0.15
    åĮºåĪ«äºİ
    0.15
    ä¸İä¼łç»Ł
    0.15
    ä¸İæĻ®éĢļ
    0.14
    è¦ģæ¯Ķ
    0.14
    Activations Density 0.846%

    No Known Activations