© 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. 54936
    Prev
    Next
    INDEX
    Explanations

    France and French language

    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
     Sears
    -0.08
    åĸ
    -0.08
    lake
    -0.07
     McMaster
    -0.07
    .nasa
    -0.07
     Tampa
    -0.07
    autant
    -0.07
    âĵĴ
    -0.07
     Sumut
    -0.07
    legg
    -0.06
    POSITIVE LOGITS
    æ³ķåĽ½
    0.14
    æ³ķè¯Ń
    0.14
     France
    0.13
     French
    0.13
    å·´é»İ
    0.13
     íĶĦëŀijìĬ¤
    0.13
    ãĥķãĥ©ãĥ³ãĤ¹
    0.13
     ÑĦÑĢанÑĨÑĥз
    0.13
    France
    0.12
    à¸Ŀรัà¹Īà¸ĩà¹Ģศส
    0.12
    Activations Density 0.967%

    No Known Activations