© 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. 19958
    Prev
    Next
    INDEX
    Explanations

    higher than expected

    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
    lat
    -0.08
    ä¸įä¸Ģæł·çļĦ
    -0.08
    åħīèį£
    -0.07
    lah
    -0.07
     구체ìłģìĿ¸
    -0.07
    ä¸įåIJĮçļĦæĺ¯
    -0.07
    åĪĨ享ä¸Ģä¸ĭ
    -0.07
    è¦ģç´§
    -0.07
    ras
    -0.07
    alk
    -0.07
    POSITIVE LOGITS
     usual
    0.10
    åİŁæĿ¥çļĦ
    0.09
    æŃ£å¸¸
    0.09
     expected
    0.09
    åİŁå®ļ
    0.09
    à¹Ģà¸Ķิม
    0.09
    é¢ĦæľŁçļĦ
    0.08
     пÑĢеж
    0.08
     previously
    0.08
    é¢ĦæľŁ
    0.08
    Activations Density 0.128%

    No Known Activations