© 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. 46746
    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
    Not in Any Lists

    No Comments

    Negative Logits
     RectTransform
    -0.27
    iculty
    -0.20
     green
    -0.20
    æŃ£åľ¨
    -0.19
    uel
    -0.19
    åħ³éĶ®æĬĢæľ¯
    -0.19
    éĢĤæŶ
    -0.19
    (named
    -0.18
     Regular
    -0.18
    缸åºĶ
    -0.18
    POSITIVE LOGITS
    :Event
    0.28
    ï¼ĥ
    0.27
    .fromRGBO
    0.26
    aeda
    0.24
     IonicPage
    0.24
    volución
    0.24
    uters
    0.23
    egov
    0.23
    geries
    0.23
    /address
    0.23
    Activations Density 0.000%

    No Known Activations