© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 719
    Prev
    Next
    INDEX
    Explanations

    coding symbols

    np_max-act-logits · gemini-2.5-flash-lite

    words related to professional or technical language, particularly in formal, scientific, medical, or business contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -labelled
    -0.20
     metic
    -0.19
     appré
    -0.18
     ëĭ¤ë§Į
    -0.18
     partager
    -0.18
    並å°ĩ
    -0.17
     ê·¸ëŁ¼
    -0.17
    çĻ«çĹ«çĹħ
    -0.17
     découvert
    -0.17
     ImageIcon
    -0.16
    POSITIVE LOGITS
    /Dk
    0.31
    [".
    0.28
    ")));
    0.28
    :"-
    0.27
    :;↵
    0.26
    ');↵↵↵↵
    0.26
    .Disclaimer
    0.26
    :'.$
    0.26
    .googlecode
    0.24
    .heroku
    0.24
    Activations Density 98.863%

    No Known Activations