© 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. 47190
    Prev
    Next
    INDEX
    Explanations

    pressure and height

    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
    енок
    -0.09
    kson
    -0.08
    ÙĪاس
    -0.08
    豺
    -0.08
    otti
    -0.08
    èĤłçĤİ
    -0.08
    å¨Ĩ
    -0.08
     déch
    -0.08
    æ´»åĬ¨ç»ĵæĿŁåIJİ
    -0.08
    ثار
    -0.08
    POSITIVE LOGITS
    -height
    0.09
    é«ĺ度
    0.09
     height
    0.09
    çļĦé«ĺ度
    0.08
    height
    0.08
     water
    0.08
     Height
    0.08
    é«ĺ度çļĦ
    0.07
    .height
    0.07
    (height
    0.07
    Activations Density 0.001%

    No Known Activations