© 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. 4621
    Prev
    Next
    INDEX
    Explanations

    spatial proximity or positioning

    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
    alez
    -0.07
    plain
    -0.07
    åĪĩåī²æľº
    -0.07
    æĢ»ç«Ļ
    -0.07
    POCH
    -0.07
    Plain
    -0.07
    _TRUNC
    -0.07
    åĭ¾
    -0.06
    æľĢæĸ°æĸĩç«ł
    -0.06
    ä»Ĭ天æĺ¯
    -0.06
    POSITIVE LOGITS
     spatial
    0.10
     proximity
    0.10
     scaffold
    0.09
    æĭīè¿ij
    0.09
    patial
    0.08
    ç´§å¯Ĩ
    0.08
     positioning
    0.08
     scaff
    0.08
    Spatial
    0.08
    æĭ¶
    0.08
    Activations Density 0.040%

    No Known Activations