© 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. 44599
    Prev
    Next
    INDEX
    Explanations

    font size

    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
    å¤ļäºİ
    -0.08
    赤水
    -0.07
    å°ijäºİ
    -0.07
    éģ¥éģ¥
    -0.07
    缸åħ³æݨèįIJ
    -0.07
    kowski
    -0.07
    æĹłæķ°
    -0.07
    hausen
    -0.07
    æĢ§è´¨çļĦ
    -0.07
    re
    -0.07
    POSITIVE LOGITS
     font
    0.11
    .fontSize
    0.11
    åŃĹä½ĵ
    0.10
    åŃĹåı·
    0.10
     fontSize
    0.09
    fontSize
    0.09
    大å°ıçļĦ
    0.09
    .font
    0.08
    -font
    0.08
    FontSize
    0.08
    Activations Density 0.065%

    No Known Activations