© 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. 8670
    Prev
    Next
    INDEX
    Explanations

    sports teams and games

    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
    ä¸įå¿ĺ
    -0.07
    rade
    -0.06
     Veg
    -0.06
    .hom
    -0.06
    å¤ĦçIJĨåIJİ
    -0.06
     Werkstatt
    -0.06
    æ»´æ°´
    -0.06
    ì§ģ
    -0.06
    æ²IJæµ´
    -0.06
    ä¹³
    -0.06
    POSITIVE LOGITS
    Rules
    0.10
     Rules
    0.10
    -playing
    0.10
     rules
    0.09
    è¦ıåīĩ
    0.09
    çļĦè§ĦåĪĻ
    0.09
    rules
    0.09
    æ¿ĢçĥĪ
    0.09
    è§ĦåĪĻ
    0.09
    è§ĦåĪĻåĴĮ
    0.09
    Activations Density 0.231%

    No Known Activations