© 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. 61373
    Prev
    Next
    INDEX
    Explanations

    Act or legislation titles

    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
    utters
    -0.07
    æİĤ
    -0.07
     kav
    -0.07
    ä¼ģä¸ļ形象
    -0.06
    ilater
    -0.06
    ä¸įæĶ¾
    -0.06
     sto
    -0.06
    acement
    -0.06
     convincing
    -0.06
    éļĶ
    -0.06
    POSITIVE LOGITS
     statute
    0.11
     Omn
    0.10
     Stat
    0.09
    大纲
    0.09
     statutes
    0.09
     Act
    0.09
    两éĥ¨
    0.08
    gesetz
    0.08
    æļĤè¡ĮåĬŀæ³ķ
    0.08
    æĿ¡ä¾ĭ
    0.08
    Activations Density 0.139%

    No Known Activations