© 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. 22317
    Prev
    Next
    INDEX
    Explanations

    medical complications

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    å½Ĵç»ĵ
    -0.05
     Further
    -0.05
    arren
    -0.05
    åħ±åIJĮ
    -0.05
    åħ±
    -0.05
    бÑĥд
    -0.05
    æĿ¥å¾Ģ
    -0.05
    ieme
    -0.05
    Shared
    -0.05
    hall
    -0.05
    POSITIVE LOGITS
    fication
    0.06
     trÆ°Æ¡ng
    0.06
    éĤĥ
    0.06
    каÑĢбо
    0.06
    irks
    0.05
     effet
    0.05
    åIJįå±±
    0.05
    oola
    0.05
     gesetz
    0.05
    ISIS
    0.05
    Activations Density 0.031%

    No Known Activations