© 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. 58707
    Prev
    Next
    INDEX
    Explanations

    examples, solutions, options, embodiments

    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
    è¿ĺæĺ¯ä¸ª
    -0.07
    çĥŃçĪ±çĶŁæ´»
    -0.07
    xDC
    -0.07
     concentr
    -0.07
    è¿ĺæĺ¯ä¸Ģ个
    -0.07
    leur
    -0.07
    ä¸įåı¯å¿½è§Ĩ
    -0.07
    xe
    -0.07
    egi
    -0.07
    roku
    -0.07
    POSITIVE LOGITS
     scenarios
    0.10
     ÙħختÙĦÙģÛĮ
    0.09
    ä¸įåIJĮç±»åŀĭçļĦ
    0.09
    ä¸įåIJĮç¨ĭ度çļĦ
    0.09
    ä¸įåIJĮè§Ĵ度
    0.08
    åĪĨåĪ«æĺ¯
    0.08
    ä¸Ģç§įæĺ¯
    0.08
    åĪĨåĪ¥æĺ¯
    0.08
     Examples
    0.08
    åħ¶ä¸ŃåĮħæĭ¬
    0.08
    Activations Density 0.249%

    No Known Activations