© 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. 22298
    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
    Not in Any Lists

    No Comments

    Negative Logits
    iliz
    -0.07
     ÙĨظر
    -0.06
    ugu
    -0.06
    æķ¦
    -0.06
    zens
    -0.06
    ascript
    -0.06
    crew
    -0.06
    zii
    -0.06
    engu
    -0.06
    penas
    -0.06
    POSITIVE LOGITS
    èµ·
    0.06
    -
    0.05
    ange
    0.05
    prof
    0.05
    åIJĦ项
    0.04
    人æĿ¥
    0.04
     -
    0.04
     H
    0.04
    说æĿ¥
    0.04
    æĢİä¹Ī
    0.04
    Activations Density 0.000%

    No Known Activations