© 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. 47879
    Prev
    Next
    INDEX
    Explanations

    home court advantage

    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
    æľ¬é¢ĺçŃĶæ¡Ī
    -0.08
    ä¸Ģç»ı
    -0.08
    æľĢç»Ī以
    -0.08
    åĬ¡
    -0.08
    æѤæĸĩ
    -0.08
    åĿĩå±ŀ
    -0.07
    åīįè¿°
    -0.07
    otos
    -0.07
    åIJİåį³åı¯
    -0.07
    Äģd
    -0.07
    POSITIVE LOGITS
    漪
    0.08
    æİ¥çĿĢ
    0.07
    ä¹Łå°±æĺ¯
    0.07
    éĤ£ä¹Ī
    0.07
    lez
    0.07
     pretty
    0.07
    ç¿
    0.07
    aget
    0.06
    {i
    0.06
    CRT
    0.06
    Activations Density 0.018%

    No Known Activations