© 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. 9556
    Prev
    Next
    INDEX
    Explanations

    medical procedures or processes

    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
    omu
    -0.08
    aldas
    -0.08
    .escape
    -0.07
    _parms
    -0.07
    immers
    -0.07
    .googleapis
    -0.07
    -serif
    -0.07
    æĦıå¤ĸçļĦ
    -0.07
     gyn
    -0.07
    Accent
    -0.06
    POSITIVE LOGITS
    ä¹ĭæīĢ以
    0.10
    çļĦæľ¬è´¨
    0.10
    æľ¬è´¨ä¸Ĭ
    0.10
    çļĦå·¥ä½ľåİŁçIJĨ
    0.10
     relies
    0.09
    å·¥ä½ľåİŁçIJĨ
    0.08
    å½Ĵæł¹
    0.08
    主è¦ģæĺ¯éĢļè¿ĩ
    0.08
     rely
    0.08
    æľ¬è´¨
    0.08
    Activations Density 0.190%

    No Known Activations