© 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. 32793
    Prev
    Next
    INDEX
    Explanations

    simplified or simplification concepts

    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
    天å¤ĸ
    -0.08
    é¢
    -0.08
    attel
    -0.07
    ross
    -0.07
    é¡»çŁ¥
    -0.07
    é¢ĸ
    -0.07
    èĵĿèī²åŃĹä½ĵ
    -0.06
    窿
    -0.06
    åľ¨æĦı
    -0.06
    OSC
    -0.06
    POSITIVE LOGITS
     simplific
    0.08
    ç®ĢåĮĸ
    0.08
     simplify
    0.08
     simpl
    0.08
     Downs
    0.08
     Simpl
    0.08
    óp
    0.07
    implify
    0.07
    æķ´çIJĨ
    0.07
    åĩij
    0.06
    Activations Density 0.037%

    No Known Activations