© 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. 46858
    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
    åİĭåĪ¶
    -0.20
    åħ¨åĬĽæīĵéĢł
    -0.19
    desired
    -0.19
    è´Ńç½®
    -0.19
    _blocking
    -0.19
     atrav
    -0.18
     potrÃł
    -0.18
    oundingBox
    -0.17
    对ä»ĸ们
    -0.17
    SOC
    -0.17
    POSITIVE LOGITS
    .ObjectMeta
    0.24
    oriously
    0.23
    ;base
    0.23
    æıĨ
    0.22
    bellion
    0.22
    ".↵↵↵↵
    0.21
    ISCO
    0.21
     nuest
    0.21
    -Identifier
    0.21
    atonin
    0.21
    Activations Density 0.000%

    No Known Activations