© 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. 1057
    Prev
    Next
    INDEX
    Explanations

    images and photos

    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
    TransparentColor
    -0.25
    èĵĬ
    -0.23
     Aires
    -0.23
    .scalablytyped
    -0.23
    Mathf
    -0.21
    RGBO
    -0.21
    nowrap
    -0.21
    idis
    -0.21
     ?><
    -0.20
    fillType
    -0.19
    POSITIVE LOGITS
     image
    0.36
     images
    0.35
    images
    0.34
    image
    0.31
    çīĪæĿĥå½Ĵ
    0.30
     view
    0.30
    åĽ¾åĥı
    0.29
    -image
    0.28
    .image
    0.26
    =image
    0.26
    Activations Density 4.203%

    No Known Activations