© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3395
    Prev
    Next
    INDEX
    Explanations

    technical contexts

    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
    ElementException
    -0.23
    .isSuccessful
    -0.22
    ):?>↵
    -0.22
    :[[
    -0.22
    ThanOrEqualTo
    -0.19
    椴
    -0.19
    :[↵
    -0.19
    ulfilled
    -0.19
    [ID
    -0.19
    ãģĹãģ¦ãģĬãģı
    -0.19
    POSITIVE LOGITS
    åĸ³
    0.22
    abouts
    0.21
     subparagraph
    0.20
    çŀł
    0.20
     beforeSend
    0.20
    aravel
    0.19
     ''){↵
    0.19
    nym
    0.19
     dataGridViewCellStyle
    0.19
    inheritDoc
    0.19
    Activations Density 0.148%

    No Known Activations