© 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. 20064
    Prev
    Next
    INDEX
    Explanations

    preserve or preservation

    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
    uality
    -0.09
    ëĿ½
    -0.08
    ually
    -0.08
    cape
    -0.08
    IALIZED
    -0.08
    oday
    -0.08
    çº¢ç´ł
    -0.07
    uate
    -0.07
    aylor
    -0.07
    regor
    -0.07
    POSITIVE LOGITS
    à¸īะà¸Ļัà¹īà¸Ļ
    0.09
    ียร
    0.08
    ä¸įäºĨ
    0.07
    OrFail
    0.07
    AspectRatio
    0.07
    iche
    0.07
    大å¸Ŀ
    0.07
     vẹn
    0.07
    รัà¸ģษา
    0.07
    主義
    0.07
    Activations Density 0.013%

    No Known Activations