© 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. 4238
    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
     fflush
    -0.21
    è¿Ķ
    -0.21
    çĭİ
    -0.21
    åľ¨è¿ĩæ¸¡æľŁ
    -0.20
    ¹
    -0.19
    éķ¿æķĪæľºåĪ¶
    -0.18
    ä»İåīį
    -0.18
     tempList
    -0.18
     tuned
    -0.18
    oblin
    -0.17
    POSITIVE LOGITS
    ä¸Ģèĩ´å¥½è¯Ħ
    0.24
    æĪ¥
    0.23
    æĭľå¸ĪåѦ
    0.23
    gunakan
    0.21
    <decimal
    0.21
    pollo
    0.21
    avigate
    0.21
     Ngb
    0.21
    datable
    0.20
    libft
    0.20
    Activations Density 0.001%

    No Known Activations