© 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. 817
    Prev
    Next
    INDEX
    Explanations

    names or foreign 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
    estroy
    -0.40
    serter
    -0.38
    ribly
    -0.38
    umblr
    -0.38
    ardu
    -0.37
    oard
    -0.37
    benh
    -0.37
    readcr
    -0.36
    ptune
    -0.36
    umbed
    -0.35
    POSITIVE LOGITS
     çĶŁåij½åij¨æľŁ
    0.28
    纰
    0.27
    Ĩ
    0.27
    ëłĩ
    0.27
    if
    0.26
    Ỹ
    0.25
    妨ç¢į
    0.25
    Ũ
    0.24
    t
    0.24
    Ẽ
    0.23
    Activations Density 11.633%

    No Known Activations