© 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. 3723
    Prev
    Next
    INDEX
    Explanations

    Expressing self

    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/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
     however
    -0.24
     поÑĤомÑĥ
    -0.23
     because
    -0.23
    åĽłä¸º
    -0.22
     Because
    -0.22
     Leban
    -0.21
    åĽłä¸ºåľ¨
    -0.21
    ä¾ĺ
    -0.20
    Because
    -0.20
    however
    -0.20
    POSITIVE LOGITS
    æ¯ķç«Ł
    0.31
    æ¯ķç«Łæĺ¯
    0.27
     presumably
    0.26
    çļĦç¼ĺæķħ
    0.26
     otherwise
    0.26
    éĤ£ä¹Īå¤ļ
    0.25
    æľ¬è´¨ä¸Ĭ
    0.25
    è¿Ļä¹Īå¤ļ
    0.23
    å®ŀåľ¨å¤ª
    0.23
     przecież
    0.23
    Activations Density 0.485%

    No Known Activations