© 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. 1078
    Prev
    Next
    INDEX
    Explanations

    in

    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
    oriously
    -0.25
    åľ°ä¸Ĭ
    -0.24
    comings
    -0.24
    ughs
    -0.24
    çİ°åľº
    -0.23
    ç½ijä¸Ĭ
    -0.23
    oretical
    -0.22
    à¸IJาà¸Ļ
    -0.21
    -bordered
    -0.21
    -ves
    -0.21
    POSITIVE LOGITS
     order
    0.32
     terms
    0.30
    ventario
    0.29
     accordance
    0.28
    serter
    0.27
    herits
    0.27
    :black
    0.27
     case
    0.26
     the
    0.26
     spite
    0.25
    Activations Density 2.884%

    No Known Activations