© 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. 3403
    Prev
    Next
    INDEX
    Explanations

    numbers and 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/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
    striction
    -0.23
    Ã¼ÄŁÃ¼
    -0.22
    utow
    -0.21
    ceive
    -0.21
    oriously
    -0.21
    activex
    -0.21
    ournemouth
    -0.20
    landers
    -0.20
    ç¨ĭ
    -0.20
    fell
    -0.20
    POSITIVE LOGITS
    建档ç«ĭ
    0.24
    ç½ijç«Ļé¦ĸ页
    0.23
    å¤įå·¥å¤į
    0.21
    EFAULT
    0.21
    èĩªçĦ¶èĢĮ
    0.21
     ****************************************
    0.19
    ä½Ļä¸ĩåħĥ
    0.19
    æĪij们认为
    0.19
    并ä¸įæĦıåij³
    0.19
     submar
    0.19
    Activations Density 0.001%

    No Known Activations