© 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. 59801
    Prev
    Next
    INDEX
    Explanations

    forests and climate

    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
     гÑĢом
    -0.07
    æĹłè¾ľ
    -0.07
    æľī好
    -0.07
    æľīæīĢæĢĿ
    -0.06
    è¾Ī
    -0.06
    æĵįä½ľä¸Ń
    -0.06
     fid
    -0.06
     positional
    -0.06
    å°ıå°ı
    -0.06
    人äºĭ
    -0.06
    POSITIVE LOGITS
    åħ¸åŀĭçļĦ
    0.10
    å¹´å¹³åĿĩ
    0.10
    éĢĤå®ľçļĦ
    0.09
    温带
    0.09
     inhabited
    0.09
     transitional
    0.09
    åħ¸åŀĭ
    0.09
    大éĥ¨åĪĨåľ°åĮº
    0.09
     transitioning
    0.09
     Ãľberg
    0.09
    Activations Density 0.125%

    No Known Activations