© 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. 750
    Prev
    Next
    INDEX
    Explanations

    technical or specific topics

    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
    أخر
    -0.26
    اÙĪÙĬØ©
    -0.21
    ICTURE
    -0.21
     isAuthenticated
    -0.20
    inine
    -0.20
    lexible
    -0.20
     yal
    -0.20
    ãģĦãĤīãģ£ãģĹãĤĥ
    -0.19
    ä¸įçŁ¥ä¸į
    -0.19
    女æĢ§æľĭåıĭ
    -0.19
    POSITIVE LOGITS
    IGHLIGHT
    0.31
    ESSAGES
    0.31
    clusão
    0.30
    تÙĦÙĥ
    0.28
     beneficiation
    0.27
    entifier
    0.27
    ornment
    0.26
    è¹ļ
    0.25
    أسÙĦ
    0.23
    /Delete
    0.23
    Activations Density 6.886%

    No Known Activations