© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1163
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    âļĹ
    -0.32
    grily
    -0.28
    家éĥ½çŁ¥éģĵ
    -0.27
     Prostit
    -0.25
    说å®ŀ
    -0.24
    çĽijåIJ¬é¡µéĿ¢
    -0.24
     ÙĪÙĩÙĨا
    -0.24
    æīĢæīĢ
    -0.24
    åĪ©çĶ¨æĤ¨çļĦ
    -0.24
    ¡´
    -0.23
    POSITIVE LOGITS
    èĢĮè¿Ļ
    0.40
     so
    0.40
    èĢĮ
    0.38
     which
    0.37
     while
    0.37
     and
    0.35
     but
    0.35
     thus
    0.33
    èĢĮä¸Ķè¿ĺ
    0.33
     thereby
    0.32
    Activations Density 2.001%

    No Known Activations