© 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. 37532
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èĩ£
    -0.07
    want
    -0.07
    bar
    -0.07
    åµĮ
    -0.07
     localize
    -0.06
    ifi
    -0.06
    баÑĢ
    -0.06
    &
    -0.06
    ilar
    -0.06
    è¶Ĭ
    -0.06
    POSITIVE LOGITS
     (${
    0.09
    请æĤ¨åħĪ
    0.08
     bezieh
    0.07
    èıģ
    0.07
    ðŁĺī
    0.07
    æĻĵ举
    0.07
     \"{
    0.07
    请访éĹ®
    0.07
    }\"
    0.07
    ;/*
    0.07
    Activations Density 0.000%

    No Known Activations