© 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. 47059
    Prev
    Next
    INDEX
    Explanations

    optimizer

    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
    ToFront
    -0.21
    crollView
    -0.21
     Platt
    -0.20
    HorizontalAlignment
    -0.20
    尽头
    -0.19
    _LICENSE
    -0.19
     modele
    -0.18
    Ã¤ÃŁig
    -0.18
    äl
    -0.18
    orgeous
    -0.18
    POSITIVE LOGITS
    PURE
    0.23
    æĿ¨æ¬¢
    0.22
    /pm
    0.21
    箧
    0.21
    pisa
    0.21
    ====↵
    0.21
    isbury
    0.21
    é²ķ
    0.20
    коло
    0.20
    ILLISE
    0.20
    Activations Density 0.002%

    No Known Activations