© 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. 628
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éparation
    -0.22
    ologne
    -0.22
    .UIManager
    -0.21
    erin
    -0.21
    trzym
    -0.20
    resden
    -0.20
    rzÄħ
    -0.20
    parer
    -0.19
    orra
    -0.19
    isse
    -0.19
    POSITIVE LOGITS
     percentage
    0.42
    çĻ¾åĪĨä¹ĭ
    0.41
    çĻ¾åĪĨ
    0.39
     (%)
    0.38
     percent
    0.36
     percentages
    0.36
    æ¯Ķä¾ĭ
    0.34
    percentage
    0.34
     fraction
    0.34
    Percentage
    0.32
    Activations Density 1.112%

    No Known Activations