© 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. 3879
    Prev
    Next
    INDEX
    Explanations

    technical or 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
    æĸ°æµªè´¢ç»ı
    -0.20
    PTS
    -0.20
    .innerHeight
    -0.19
     QDir
    -0.18
     audit
    -0.18
    ä¸ĢéĹª
    -0.18
    ÙĬست
    -0.18
     sluts
    -0.18
    ixel
    -0.17
    полиÑĤ
    -0.17
    POSITIVE LOGITS
    Serviço
    0.26
    ä¸ĭéĿ¢æĺ¯å°ı
    0.23
    urança
    0.22
    Debe
    0.22
     Derne
    0.21
    é½IJ
    0.20
    .MULT
    0.19
    ãħĩ
    0.19
    Slf
    0.19
    onders
    0.19
    Activations Density 0.001%

    No Known Activations