© 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. 44260
    Prev
    Next
    INDEX
    Explanations

    new dictionary

    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
    ä¸ĩæĪ·
    -0.07
    style
    -0.07
     style
    -0.06
    庶
    -0.06
    æĴ
    -0.06
    å±ģ
    -0.06
    ç´łæľī
    -0.06
    æŃ»ä¸į
    -0.06
    æĹ·
    -0.06
     Lut
    -0.06
    POSITIVE LOGITS
    æĺ¯ç»ıè¿ĩ
    0.12
    åIJİçļĦ
    0.11
     transformed
    0.10
    formed
    0.10
    å·²ç»ı没æľī
    0.10
    çŃīæĸ°
    0.09
    åĮĸäºĨ
    0.09
    äºĨçļĦ
    0.09
    (after
    0.09
    è°ĥæķ´åIJİ
    0.09
    Activations Density 0.193%

    No Known Activations