© 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. 43144
    Prev
    Next
    INDEX
    Explanations

    because of

    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
    ä»»ä½ķä¸Ģ个
    -0.08
    ertes
    -0.07
    locales
    -0.07
    æľĢç¾İçļĦ
    -0.07
    æŁIJä¸Ģ个
    -0.07
     mattered
    -0.07
    æľĢåħ·
    -0.07
     peor
    -0.07
    æľīçĶ¨çļĦ
    -0.07
    äºĪ以
    -0.07
    POSITIVE LOGITS
    ç§įç§įåİŁåĽł
    0.14
     lack
    0.13
     adanya
    0.11
     reliance
    0.10
    åIJĦç§įåİŁåĽł
    0.10
    æ¯ķç«Łæĺ¯
    0.09
    çļĦç¼ĺæķħ
    0.09
    åħ¶åľ¨
    0.08
     presence
    0.08
    ä¸įå®Įåħ¨ç»Łè®¡
    0.08
    Activations Density 0.122%

    No Known Activations