© 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. 20860
    Prev
    Next
    INDEX
    Explanations

    court and judge proceedings

    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
    еÑģо
    -0.07
    ç»ı缸åħ³éĥ¨éŨæī¹åĩĨ
    -0.07
    Encoding
    -0.07
     пÑĢеÑĤен
    -0.07
    åħļ代ä¼ļ
    -0.07
     revend
    -0.07
    linky
    -0.07
    æĬĹè®®
    -0.07
    ayu
    -0.07
     rivend
    -0.07
    POSITIVE LOGITS
    审çIJĨ
    0.10
     adjud
    0.08
     hearing
    0.08
    åĨ³å®ļæĺ¯åIJ¦
    0.08
    å®¡æŁ¥
    0.08
    ç»ĦæĪIJåIJĪè®®åºŃ
    0.08
     judges
    0.08
     discretion
    0.07
     Judges
    0.07
    éĿ¢åīį
    0.07
    Activations Density 0.299%

    No Known Activations