© 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. 16852
    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
    óta
    -0.06
    رÙĪÙĬ
    -0.06
    tria
    -0.06
    aret
    -0.06
    ئا
    -0.06
    roda
    -0.06
    winkel
    -0.05
    สิ
    -0.05
    æľīä¸ĢèĤ¡
    -0.05
    åѦæľīæīĢ
    -0.05
    POSITIVE LOGITS
     scratch
    0.06
    uell
    0.06
    scription
    0.06
    æľ¬
    0.06
    gether
    0.05
    ployment
    0.05
    .setLevel
    0.05
     prom
    0.05
    uch
    0.05
     hereby
    0.05
    Activations Density 0.000%

    No Known Activations