© 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. 16628
    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
    oking
    -0.05
     dick
    -0.05
    åij¼
    -0.05
     Clar
    -0.05
    è¯ķè¡Į
    -0.05
    伤æĥħ
    -0.05
     Erd
    -0.05
     raff
    -0.05
     Guarda
    -0.05
    ys
    -0.04
    POSITIVE LOGITS
    å·®ä¸į
    0.06
    æĪijåIJĹ
    0.06
     pront
    0.06
    次çļĦ
    0.06
     livré
    0.06
    execution
    0.06
    ä¸įå°±æĺ¯
    0.06
    空空
    0.06
    没æľīæŶéĹ´
    0.06
    hum
    0.06
    Activations Density 0.000%

    No Known Activations