© 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. 709
    Prev
    Next
    INDEX
    Explanations

    technical specification details

    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
    ãģĦãĤĭ
    -0.35
    set
    -0.28
    so
    -0.26
    ness
    -0.26
    s
    -0.26
     timeval
    -0.26
    ооÑĢÑĥж
    -0.26
    ss
    -0.26
    re
    -0.25
    son
    -0.25
    POSITIVE LOGITS
    âļĹ
    0.43
    ðŁĵIJ
    0.40
    earch
    0.32
    utow
    0.31
    âĹĤ
    0.31
    /Dk
    0.30
    %";↵
    0.29
    ðŁĵĻ
    0.29
    ",-
    0.28
    legant
    0.28
    Activations Density 11.630%

    No Known Activations