© 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. 22525
    Prev
    Next
    INDEX
    Explanations

    coronary artery

    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
    à¹Īà¸ĩ
    -0.07
    dda
    -0.07
    人æ°ijåħ±åĴĮåĽ½
    -0.07
    andes
    -0.07
    à¸ģุล
    -0.07
    ÏĦÎŃ
    -0.07
    é¢ģ
    -0.07
    cca
    -0.07
    imbul
    -0.06
    ève
    -0.06
    POSITIVE LOGITS
     again
    0.09
    Again
    0.07
     Again
    0.07
    åĨį次
    0.07
    again
    0.07
     M
    0.05
     erneut
    0.05
     C
    0.05
     c
    0.05
    åıĪä¼ļ
    0.05
    Activations Density 0.005%

    No Known Activations