© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2736
    Prev
    Next
    INDEX
    Explanations

    sports leagues and seasons

    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
    kina
    -0.07
     EVER
    -0.07
     bipartisan
    -0.07
     keynote
    -0.06
    aken
    -0.06
    æ²¹æĢ§
    -0.06
    æī¿æĭħä¸ĢåĪĩ
    -0.06
    ç«ĭåľ¨
    -0.06
    åŁĭåľ¨
    -0.06
     Roe
    -0.06
    POSITIVE LOGITS
     اÙĦدرجة
    0.09
     league
    0.09
     standings
    0.09
     leagues
    0.08
     Rings
    0.08
    çĻ½éĵ¶
    0.08
    ostr
    0.08
     playoffs
    0.08
    èģĶèµĽ
    0.08
    логи
    0.08
    Activations Density 0.451%

    No Known Activations