© 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. 45654
    Prev
    Next
    INDEX
    Explanations

    Telegram bot code

    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
    discord
    -0.23
    驺
    -0.23
    èĩ¾
    -0.22
    ("(%
    -0.20
    豨
    -0.20
    Ø®ÙĦÙģ
    -0.19
    |,↵
    -0.19
    recht
    -0.19
    河西
    -0.19
     LinkedHashMap
    -0.19
    POSITIVE LOGITS
    bove
    0.23
    bairro
    0.23
    rchive
    0.23
     Wilkinson
    0.23
    /*↵
    0.23
    pollo
    0.22
     necessitÃł
    0.22
    /MPL
    0.22
    estroy
    0.22
    swire
    0.21
    Activations Density 0.006%

    No Known Activations