© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1983
    Prev
    Next
    INDEX
    Explanations

    statistics data

    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
     loadImage
    -0.24
    æĭĥ
    -0.24
     imgUrl
    -0.23
    被èªī
    -0.23
     semiclassical
    -0.22
     Fotos
    -0.21
     LinearGradient
    -0.21
    âĤµ
    -0.21
    为客æĪ·
    -0.21
    å¤ĸè§Ĥ
    -0.21
    POSITIVE LOGITS
    ç»Łè®¡
    0.36
     statistics
    0.35
    ç»Łè®¡æķ°æį®
    0.34
    æķ°æį®
    0.33
     data
    0.32
     Statistics
    0.32
    çļĦæķ°æį®
    0.31
     annual
    0.30
    åħ¨åĽ½
    0.30
     annually
    0.30
    Activations Density 4.279%

    No Known Activations