© 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. 4290
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     newcom
    -0.30
    ìĭ¶
    -0.26
    -Compatible
    -0.24
     ASUS
    -0.24
    glÄħd
    -0.23
    /pm
    -0.23
    quartered
    -0.23
    etz
    -0.23
    ãİŀ
    -0.23
    âľª
    -0.22
    POSITIVE LOGITS
     fro
    0.21
     itself
    0.20
    Editor
    0.20
    æľ¬èº«
    0.20
     themselves
    0.18
     moot
    0.18
     ware
    0.18
    :
    0.18
     dam
    0.18
     dep
    0.18
    Activations Density 0.000%

    No Known Activations