© 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. 2236
    Prev
    Next
    INDEX
    Explanations

    Czech words

    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
     svo
    -0.29
    oproject
    -0.29
     kone
    -0.27
    estroy
    -0.24
     Komm
    -0.24
    kich
    -0.23
     rekl
    -0.23
     potrÃł
    -0.22
    .ru
    -0.22
    AndGet
    -0.21
    POSITIVE LOGITS
     Czech
    0.25
     RequestMethod
    0.24
    ÐŁÐ¾Ð´ÑĢоб
    0.24
    âĢ¦↵↵↵↵
    0.22
    人æ°ijæľįåĬ¡
    0.22
     lingerie
    0.22
     zdarma
    0.21
     bezpo
    0.21
     Templ
    0.20
    é¾ĥ
    0.20
    Activations Density 0.774%

    No Known Activations