© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4145
    Prev
    Next
    INDEX
    Explanations

    code symbols

    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
    Negative Logits
    räg
    -0.21
     scrimmage
    -0.21
    reactstrap
    -0.20
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.20
    çīĪæĿĥå½Ĵ
    -0.20
    ç½ijé¦ĸ页
    -0.19
    _completion
    -0.19
    âĿ¯
    -0.19
    åĢ¼å¾Ĺä¸Ģ
    -0.19
     Schumer
    -0.19
    POSITIVE LOGITS
    Çľ
    0.27
    []{↵
    0.23
    Reducers
    0.21
    avenport
    0.21
    åIJĪãģĦ
    0.20
    饺
    0.20
     tempList
    0.20
    _IL
    0.19
    XObject
    0.19
     []);↵↵
    0.19
    Activations Density 0.001%

    No Known Activations