© 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. 43225
    Prev
    Next
    INDEX
    Explanations

    court names and judges

    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
    Ĺı
    -0.07
    guas
    -0.07
    leon
    -0.07
    à¹Ģà¸ķà¸Ńรà¹Į
    -0.07
    ç£Ĭ
    -0.06
    еÑģо
    -0.06
    ä¹Łå¤§
    -0.06
    kees
    -0.06
    ä½łåıªè¦ģ
    -0.06
    ãĥ¬ãĥĥ
    -0.06
    POSITIVE LOGITS
    鬣
    0.07
    åŁ¹
    0.07
    符
    0.07
    åľ¨æł¡æľŁéĹ´
    0.07
    ib
    0.07
    æij§
    0.07
    寻
    0.07
    ÙĪارÙĩ
    0.06
    REST
    0.06
    oli
    0.06
    Activations Density 0.156%

    No Known Activations