© 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. 22537
    Prev
    Next
    INDEX
    Explanations

    valve disease or stenosis

    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
    Negative Logits
    ever
    -0.06
     luk
    -0.06
    æij©çĻ»
    -0.05
    кÑĥÑĢÑģ
    -0.05
    кÑĥÑĢ
    -0.05
    Eu
    -0.05
     uitge
    -0.05
    黼
    -0.05
    头èĦij
    -0.05
    etzes
    -0.05
    POSITIVE LOGITS
    ROWS
    0.06
     طب
    0.06
    央è¡Į
    0.06
    rag
    0.06
    orate
    0.06
    nants
    0.06
    airy
    0.06
    åĨľåķĨéĵ¶è¡Į
    0.05
    ä¸Ĭ马
    0.05
    åĪºèĢ³
    0.05
    Activations Density 0.022%

    No Known Activations