© 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. 1449
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    "
    -0.27
    سؤ
    -0.25
    bellion
    -0.25
     disappe
    -0.25
     honda
    -0.25
     tamil
    -0.25
     pestic
    -0.23
    ç¥Ľæĸij
    -0.23
    Ø¥ÙĦ
    -0.23
     seiz
    -0.22
    POSITIVE LOGITS
    ','');↵
    0.31
    âĬĦ
    0.29
    (*)(
    0.29
    [".
    0.29
    ;br
    0.26
    ].'
    0.25
    Uvs
    0.25
    ','%
    0.25
    /Dk
    0.25
    assador
    0.24
    Activations Density 0.242%

    No Known Activations