© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52064
    Prev
    Next
    INDEX
    Explanations

    coordinate transformation

    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
    Negative Logits
    èĢĮ为
    -0.07
     additions
    -0.07
    elman
    -0.07
    æľīåĬł
    -0.07
    ç°
    -0.07
     prestig
    -0.07
    åĬłèµ·æĿ¥
    -0.07
    croft
    -0.07
    azor
    -0.07
     Claro
    -0.07
    POSITIVE LOGITS
     correspondence
    0.09
    转æį¢
    0.09
     relationship
    0.08
     transforms
    0.08
     mapping
    0.08
    转æį¢ä¸º
    0.08
    æĺłå°Ħ
    0.08
    æĽ´æĸ¹ä¾¿
    0.08
     transformation
    0.08
     conversion
    0.08
    Activations Density 0.005%

    No Known Activations