© 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. 9937
    Prev
    Next
    INDEX
    Explanations

    optimized, because, if

    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
    æĢİä¹ĪåĬŀåij¢
    -0.08
    ä½Ĩæĺ¯ä»ĸ们
    -0.08
    çľĭçľĭåIJ§
    -0.08
    anjian
    -0.08
    ä½łçŁ¥éģĵåIJĹ
    -0.08
    çļĦåIJĹ
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.07
     пÑĢавда
    -0.07
    اط
    -0.07
    è¯·ä½ł
    -0.07
    POSITIVE LOGITS
    æĹ¢è¦ģ
    0.09
    éģ¿åħįåĩºçİ°
    0.08
    ä½ĵçİ°åĩº
    0.08
    æ¯ķç«Łæĺ¯
    0.08
    ä¸įè¦ģ
    0.08
    çķĻåĩº
    0.08
    æ¯ķç«Ł
    0.08
    å¤ļçĶ¨
    0.08
    çķ¢ç«Ł
    0.07
     legyen
    0.07
    Activations Density 0.001%

    No Known Activations