© 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. 1000
    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
    rippling
    -0.25
     koje
    -0.23
    .Paths
    -0.23
    .GetInt
    -0.22
    -Bold
    -0.21
     consect
    -0.21
    微软éĽħé»ij
    -0.20
    .MouseDown
    -0.19
    logen
    -0.19
    ADIO
    -0.18
    POSITIVE LOGITS
     accuses
    0.22
    toISOString
    0.21
    valueOf
    0.20
    omat
    0.20
    	 č↵
    0.19
     âĹĭ
    0.18
     defends
    0.18
    ropp
    0.18
    ');"
    0.18
    ungs
    0.18
    Activations Density 0.001%

    No Known Activations