© 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. 3048
    Prev
    Next
    INDEX
    Explanations

    headings or sections

    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
    åij¸
    -0.23
    æ¸İ
    -0.21
    æ»ļæ»ļ
    -0.21
    Segoe
    -0.20
    NSNumber
    -0.20
    .spi
    -0.20
     (){
    -0.20
     HtmlWebpackPlugin
    -0.19
     dõ
    -0.19
     pal
    -0.18
    POSITIVE LOGITS
    udeau
    0.24
     Thumbnails
    0.23
    herits
    0.23
     DISCLAIMER
    0.22
    hci
    0.21
     McA
    0.20
    ngrx
    0.19
    ðŁĵIJ
    0.19
    reeNode
    0.19
    ãģĩ
    0.19
    Activations Density 0.012%

    No Known Activations