© 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. 11577
    Prev
    Next
    INDEX
    Explanations

    approval and certification

    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
    uzu
    -0.08
    -vars
    -0.08
    åıijçİ°èĩªå·±
    -0.07
    ä½ĨæĦ¿
    -0.07
    argest
    -0.07
    ç´Ħå®ļ
    -0.07
    Õ¼
    -0.07
    ipping
    -0.07
    à¤Ńा
    -0.07
    ä¸įçIJĨ
    -0.07
    POSITIVE LOGITS
    认è¯ģ
    0.10
    认åı¯
    0.10
     certification
    0.09
    审å®ļ
    0.09
     approval
    0.09
    认åı¯åĴĮ
    0.08
     certify
    0.08
    认åı¯çļĦ
    0.08
    -tested
    0.08
     testing
    0.08
    Activations Density 0.133%

    No Known Activations