© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4372
    Prev
    Next
    INDEX
    Explanations

    atherosclerosis

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸ŀ
    -0.21
    天èĬ±
    -0.21
    ä»Ļ
    -0.20
     Büyük
    -0.19
    .DateField
    -0.19
    ä¿Ŀç¨İ
    -0.19
    baum
    -0.19
    /gpl
    -0.18
    .lists
    -0.18
    åĮĻ
    -0.18
    POSITIVE LOGITS
    è¡Ģ管
    0.29
    è¡Ģåİĭ
    0.27
    åĬ¨èĦī
    0.27
     coronary
    0.24
    .mipmap
    0.24
    theros
    0.24
     angi
    0.23
     endoth
    0.23
    vascular
    0.23
    ortic
    0.23
    Activations Density 1.190%

    No Known Activations