© 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. 2217
    Prev
    Next
    INDEX
    Explanations

    sports matches between countries

    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
    éŃĶæĹı
    -0.07
    uson
    -0.06
    èĢģå¤ĸ
    -0.06
     mistress
    -0.06
     заÑĢÑĥбежнÑĭÑħ
    -0.06
    -Isl
    -0.06
    eah
    -0.06
    åĮĪ奴
    -0.06
    obi
    -0.06
    -describedby
    -0.06
    POSITIVE LOGITS
    ä¸İåĽ½åĨħ
    0.08
    åĴĮæĻ®éĢļ
    0.08
    ä¸Ńæĸ¹
    0.08
    åľ¨åŃ¦ä¹łä¸Ĭ
    0.07
    主è§Ĵ
    0.07
    ç®Ģä½ĵä¸Ńæĸĩ
    0.07
    .AspNetCore
    0.07
    ä¸ŃåĽ½æĶ¿åºľ
    0.07
    å°ıåѦèĭ±è¯Ń
    0.07
    ä¸İæĻ®éĢļ
    0.07
    Activations Density 0.575%

    No Known Activations