© 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. 64844
    Prev
    Next
    INDEX
    Explanations

    FIFA referee

    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
    evos
    -0.07
    irsi
    -0.07
    è¿ŀæĹ¥æĿ¥
    -0.07
    åĽ¾åĪĨç±»åı·
    -0.07
    assi
    -0.07
    æķĻäºİ
    -0.07
     Barrel
    -0.06
    OrDefault
    -0.06
    ATAB
    -0.06
    çļĦæĦıè¯Ĩ
    -0.06
    POSITIVE LOGITS
    ych
    0.07
    åĤ¢
    0.07
    æķ´ä¸ªéĹ®é¢ĺ
    0.07
    رÙħ
    0.07
    æķ´ä½ĵçļĦ
    0.07
    æķ´ä¸ª
    0.07
     Crimea
    0.06
    ç»ıä¹ħ
    0.06
     entire
    0.06
    schemas
    0.06
    Activations Density 0.168%

    No Known Activations