© 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. 1366
    Prev
    Next
    INDEX
    Explanations

    at

    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
     kaps
    -0.24
    åŃ£åIJİ
    -0.22
    polator
    -0.22
     snapchat
    -0.21
     arrang
    -0.20
     mamma
    -0.20
     setBackgroundColor
    -0.20
    erÃł
    -0.20
    åѦåīį
    -0.20
     seiz
    -0.19
    POSITIVE LOGITS
    /Dk
    0.36
    kinson
    0.32
    rophy
    0.29
    lassian
    0.29
     least
    0.28
    ungalow
    0.28
    ,www
    0.28
    rophic
    0.26
     times
    0.26
    tempts
    0.25
    Activations Density 1.054%

    No Known Activations