© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22634
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    æĹłè®ºä½łæĺ¯
    -0.07
    ä»ĸ被
    -0.07
    她被
    -0.06
    enville
    -0.06
    æİĪ
    -0.06
    ruh
    -0.06
    å¹´ç§ĭåŃ£
    -0.06
    æĪij被
    -0.06
    çal
    -0.06
    åħ±åŃĺ
    -0.06
    POSITIVE LOGITS
    æķĮ
    0.05
    é¥
    0.05
    0.05
    avi
    0.05
    举åĬ¨
    0.05
    "..
    0.04
    {$
    0.04
     Haf
    0.04
    ä¸įç¡®å®ļ
    0.04
    é½IJ
    0.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.