© 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. 46860
    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
    ughter
    -0.24
    OOT
    -0.21
    çĸµ
    -0.20
    .pb
    -0.20
    âĨ©
    -0.19
    âĹĦ
    -0.19
    erness
    -0.19
    DIRECTORY
    -0.18
    olesale
    -0.18
    ëIJĺ기
    -0.18
    POSITIVE LOGITS
    èı½
    0.25
    ampionship
    0.23
    psc
    0.21
    楣
    0.19
    ceipt
    0.19
     GetById
    0.19
    uetype
    0.18
     patent
    0.18
     Pat
    0.18
    UIKit
    0.18
    Activations Density 0.000%

    No Known Activations