© 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. 1061
    Prev
    Next
    INDEX
    Explanations

    code and abbreviations

    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
    rippling
    -0.31
     lokale
    -0.28
     AsyncStorage
    -0.26
     annonces
    -0.23
     gratuits
    -0.23
     apologise
    -0.23
     helf
    -0.22
    ryfall
    -0.21
     sito
    -0.21
    å¤ļãģĦ
    -0.21
    POSITIVE LOGITS
    ummings
    0.37
    stants
    0.36
    ynthia
    0.35
    .AutoComplete
    0.31
    iêu
    0.30
    ornings
    0.30
    readcr
    0.30
    esteem
    0.30
    hế
    0.30
    urnished
    0.29
    Activations Density 8.850%

    No Known Activations