© 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. 7884
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and Indonesian definitions

    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
    ä¹Łæľī
    -0.06
    6
    -0.06
    èĢĮå®ļ
    -0.06
    ä¹ŁåĮħæĭ¬
    -0.06
    ä¸į说
    -0.06
    åĮħæĭ¬
    -0.06
    cast
    -0.06
    æľīåĩł
    -0.06
    è¿ĺåĮħæĭ¬
    -0.06
    åı¯æĥ³èĢĮçŁ¥
    -0.06
    POSITIVE LOGITS
    çŃīéĥ½æĺ¯
    0.11
     ÑıвлÑıÑİÑĤÑģÑı
    0.09
    è¿Ļæĺ¯å¯¹
    0.09
     merupakan
    0.09
     adalah
    0.09
    æ³ķæĺ¯
    0.09
     denotes
    0.09
    arendra
    0.09
    -plugins
    0.08
    à¸Ļีà¹īà¹Ģà¸Ľà¹ĩà¸Ļ
    0.08
    Activations Density 0.028%

    No Known Activations