© 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. 18566
    Prev
    Next
    INDEX
    Explanations

    relative speed, angle, phase, or position

    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
    ä¸įå°ij
    -0.08
    æĪĸåĽł
    -0.07
    cdf
    -0.07
    åĬ¨è¾Ħ
    -0.07
    èĥ½è§ģ度
    -0.07
    æģ©
    -0.06
    ä¸įä¹ı
    -0.06
    uluk
    -0.06
    Bounds
    -0.06
    æ¯ķç«Ł
    -0.06
    POSITIVE LOGITS
     strategically
    0.11
     deliberately
    0.11
    çļĦ缮çļĦæĺ¯
    0.10
    缮çļĦåľ¨äºİ
    0.10
     purposely
    0.10
    缮çļĦæĺ¯ä¸ºäºĨ
    0.10
     nhằm
    0.10
     carefully
    0.09
    缮çļĦæĺ¯
    0.09
    å·§å¦Ļ
    0.09
    Activations Density 0.069%

    No Known Activations