© 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. 978
    Prev
    Next
    INDEX
    Explanations

    visual elements

    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
    RGBO
    -0.27
     ${({
    -0.24
    Uvs
    -0.22
    popover
    -0.21
    epy
    -0.20
    prene
    -0.20
    preneur
    -0.20
    lush
    -0.20
    æįĥ
    -0.20
    Ç
    -0.20
    POSITIVE LOGITS
     shown
    0.35
    æīĢ示
    0.29
     left
    0.27
     arrows
    0.27
    shown
    0.26
     mag
    0.25
    代表
    0.25
     blue
    0.25
     show
    0.25
    æłĩ注
    0.24
    Activations Density 0.646%

    No Known Activations