© 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. 52134
    Prev
    Next
    INDEX
    Explanations

    geographical distance

    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
    ubb
    -0.08
    peq
    -0.08
    jeÄį
    -0.08
    缮ä¸Ń
    -0.08
    tav
    -0.07
    社ä¼ļåĴĮè°IJ
    -0.07
    家éŨåı£
    -0.07
    lds
    -0.07
    .DO
    -0.07
     Sond
    -0.07
    POSITIVE LOGITS
    éģ¥è¿ľ
    0.11
    å¼Ĥåľ°
    0.11
    åľ°åŁŁ
    0.11
     distant
    0.11
    è¿ľçļĦ
    0.10
    跨度
    0.10
    缸è·Ŀ
    0.10
     geographical
    0.10
    åįĥéĩĮ
    0.10
    éģ¥è¿ľçļĦ
    0.10
    Activations Density 0.211%

    No Known Activations