© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 170
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    foundland
    -0.23
    kich
    -0.23
    ossal
    -0.21
    ndern
    -0.21
    ifestyle
    -0.21
    igmoid
    -0.20
    enery
    -0.20
    szÄĻ
    -0.20
    ourcem
    -0.20
    isContained
    -0.20
    POSITIVE LOGITS
    .assertNull
    0.22
    âĶĤ
    0.20
    ä¿ij
    0.19
    :numel
    0.19
    濯
    0.19
    RESH
    0.19
     mor
    0.19
    ÙħÙĤاÙĦات
    0.18
    æĢ§ä»·
    0.18
     Intel
    0.18
    Activations Density 0.011%

    No Known Activations