© 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. 52091
    Prev
    Next
    INDEX
    Explanations

    set builder notation

    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
     Prez
    -0.07
    åĮĹä¸Ĭ
    -0.06
    rob
    -0.06
     Äı
    -0.06
     robo
    -0.06
     Soft
    -0.06
    thora
    -0.06
    æIJŀ好
    -0.06
    éĢłçī©
    -0.06
    regar
    -0.06
    POSITIVE LOGITS
    转æį¢
    0.10
    èĵī
    0.09
    转åĮĸ
    0.08
    转æį¢ä¸º
    0.08
    åĮĸåĴĮ
    0.08
     karÅŁ
    0.08
     equivalents
    0.08
    åĮĸ为
    0.08
    è½īæıĽ
    0.08
    åĮĸçļĦ
    0.08
    Activations Density 0.068%

    No Known Activations