© 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. 45702
    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
    游æĪıå½ĵä¸Ń
    -0.25
    #ab
    -0.24
    åĩ¡æľ¬ç½ij
    -0.23
    bbie
    -0.22
    姹
    -0.22
    éĵİ
    -0.21
    intégr
    -0.20
    %X
    -0.19
    ëĨ¨
    -0.19
    .IsNullOr
    -0.19
    POSITIVE LOGITS
    -Origin
    0.20
    ácil
    0.20
    alers
    0.19
    秦
    0.19
    dba
    0.19
    /part
    0.19
    ettes
    0.19
    enor
    0.19
    }'",
    0.18
    :green
    0.18
    Activations Density 0.000%

    No Known Activations