© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 541
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    enegro
    -0.23
    Äĩi
    -0.21
     Saturdays
    -0.20
    ornings
    -0.20
    èĢĮåİ»
    -0.19
    æĺ¥ç§ĭ
    -0.19
    éĵ©
    -0.19
    è®
    -0.19
    æĿ¨æ¬¢
    -0.19
    achuset
    -0.19
    POSITIVE LOGITS
    éĶĵ
    0.23
    (){}↵↵
    0.22
    благо
    0.21
    对åħ¶çľŁå®ŀ
    0.21
    té
    0.20
    lay
    0.20
    ÑĤÑĢадиÑĨион
    0.20
    æŃ£å¼ı
    0.20
     nowrap
    0.19
    noticed
    0.19
    Activations Density 0.522%

    No Known Activations