© 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. 44247
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific symbols

    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
    满
    -0.08
    whose
    -0.07
    è£ħ满
    -0.07
     whose
    -0.07
    ä»»ä½ķä¸Ģ个
    -0.06
    亦åı¯
    -0.06
    çĥŃéŨæłĩçŃ¾
    -0.06
     renamed
    -0.06
    å¥łå®ļ
    -0.06
    cores
    -0.06
    POSITIVE LOGITS
    使çĶ¨äºĨ
    0.10
    çĸijä¼¼
    0.09
    ä¼¼ä¹İ
    0.08
    çĶ¨çļĦæĺ¯
    0.08
     punctuation
    0.08
    ä¼¼ä¹İæĺ¯
    0.08
    çĶ¨äºĨ
    0.08
    æĭ¬
    0.08
    使çĶ¨çļĦæĺ¯
    0.08
     text
    0.08
    Activations Density 0.006%

    No Known Activations