© 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. 47686
    Prev
    Next
    INDEX
    Explanations

    Chinese punctuation and code endings

    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
    PAN
    -0.07
    -guide
    -0.07
    hints
    -0.07
    åIJ»
    -0.07
     Cristian
    -0.07
    åIJĽ
    -0.07
    æl
    -0.07
    Began
    -0.07
    (found
    -0.06
     StringComparison
    -0.06
    POSITIVE LOGITS
    è¿Ļæł·
    0.09
    å§Ĩæĸ¯
    0.08
     Trinh
    0.08
    mast
    0.07
    éģį
    0.07
    è¿Ļæł·åŃIJ
    0.07
    è¿Ļæł·å°±
    0.07
    è¿Ļæł·ä¸ĢæĿ¥
    0.07
     inaccessible
    0.07
    æľīæį®
    0.07
    Activations Density 0.234%

    No Known Activations