© 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. 1038
    Prev
    Next
    INDEX
    Explanations

    legislation and rules

    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
     imageURL
    -0.33
    /mit
    -0.31
     imgUrl
    -0.31
     imagePath
    -0.29
     imageName
    -0.28
    subplot
    -0.26
     scaleY
    -0.26
     licensors
    -0.26
     keypoints
    -0.25
     imageSize
    -0.24
    POSITIVE LOGITS
    åĩºåı°
    0.30
    -scrollbar
    0.26
     implementation
    0.26
    èĮķ
    0.25
    æĶ¹éĿ©
    0.25
    ccoli
    0.24
    alité
    0.24
    ç«ĭæ³ķ
    0.23
    hud
    0.23
    修订
    0.23
    Activations Density 3.284%

    No Known Activations