© 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. 1153
    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
    e
    -0.28
    o
    -0.23
    h
    -0.23
    ä½Ĩæĺ¯å¯¹äºİ
    -0.23
    ç»ıéªĮåĢ¼
    -0.23
    l
    -0.22
    ESSAGES
    -0.22
    没æľī太大
    -0.22
    s
    -0.22
    y
    -0.22
    POSITIVE LOGITS
    onestly
    0.26
    éparation
    0.26
    ialized
    0.25
     ÑĢаÑģÑģказÑĭва
    0.24
    documento
    0.24
    #ga
    0.23
    :[[
    0.23
    toolbox
    0.23
     BaseEntity
    0.23
    undreds
    0.22
    Activations Density 5.159%

    No Known Activations