© 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. 2614
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    indr
    -0.22
    TreeWidgetItem
    -0.22
     ******************************************************************************↵
    -0.22
    urance
    -0.20
    ãĢĴ
    -0.19
     Tavern
    -0.19
     dirent
    -0.19
    西路
    -0.19
     Tories
    -0.19
     grantResults
    -0.19
    POSITIVE LOGITS
    ]={↵
    0.24
    .numberOfLines
    0.24
    ?action
    0.23
    (WIN
    0.23
    )))),
    0.23
    UIFont
    0.22
    :[[
    0.22
    çį¾
    0.22
    [vi
    0.22
    CCCC
    0.21
    Activations Density 0.362%

    No Known Activations