© 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. 706
    Prev
    Next
    INDEX
    Explanations

    French 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
     automát
    -0.33
    Descricao
    -0.31
    são
    -0.30
     Sexo
    -0.29
    Serviço
    -0.29
     básica
    -0.29
     pione
    -0.29
     especÃŃfica
    -0.28
     ragaz
    -0.28
     défini
    -0.28
    POSITIVE LOGITS
     dames
    0.34
     baiser
    0.33
     adulte
    0.32
     célib
    0.30
    ´s
    0.28
     francaise
    0.28
    /sweetalert
    0.27
    æĿľåħ°
    0.26
     ÐŁÐµÑĢе
    0.26
     AuÃŁen
    0.26
    Activations Density 2.663%

    No Known Activations