© 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-CHAT-65K
    7. 45605
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    afür
    -0.20
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.19
    涴
    -0.19
    FN
    -0.18
    clusive
    -0.18
    Æł
    -0.18
     Hind
    -0.18
    ÙħÙĨØ°
    -0.18
    ÙĦاÙĤØ©
    -0.18
    ´Ģ
    -0.17
    POSITIVE LOGITS
    ÑĤвеÑĢжда
    0.28
     ?>↵↵↵
    0.27
    undy
    0.22
    stituição
    0.21
    pollo
    0.20
    gunakan
    0.19
    .DialogInterface
    0.19
    iguiente
    0.19
    owntown
    0.19
    .React
    0.19
    Activations Density 0.000%

    No Known Activations