© 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. 45481
    Prev
    Next
    INDEX
    Explanations

    variable declaration

    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/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
     nues
    -0.25
     holland
    -0.24
     ámb
    -0.24
     vej
    -0.23
     peru
    -0.22
    o
    -0.22
     milan
    -0.22
     venez
    -0.21
     desar
    -0.21
    vanished
    -0.21
    POSITIVE LOGITS
    /Dk
    0.36
    éparation
    0.30
    upertino
    0.29
    (Android
    0.28
    (iOS
    0.28
    'icon
    0.27
    .§
    0.27
    (Have
    0.27
    .borderColor
    0.27
    skirts
    0.27
    Activations Density 0.007%

    No Known Activations