© 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. 3210
    Prev
    Next
    INDEX
    Explanations

    carry

    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
    abyrin
    -0.24
    ÐŁÐ¾Ð´ÑĢобнее
    -0.24
    WXYZ
    -0.24
    æĻ°
    -0.23
    ---</
    -0.23
    Ỹ
    -0.23
    #ga
    -0.22
    )./
    -0.22
    "w
    -0.22
    )))),
    -0.21
    POSITIVE LOGITS
     carry
    0.27
     carrying
    0.26
     carried
    0.24
     load
    0.24
    .load
    0.24
    è´Łæĭħ
    0.24
     loadData
    0.23
    è´Łèį·
    0.23
     LOAD
    0.23
    Load
    0.23
    Activations Density 0.088%

    No Known Activations