© 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. 589
    Prev
    Next
    INDEX
    Explanations

    code/programming

    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
     novitÃł
    -0.35
    ﹤
    -0.31
     Marlins
    -0.30
     Canucks
    -0.29
     desar
    -0.27
     beneficiation
    -0.27
     tantra
    -0.27
     modalitÃł
    -0.27
     qualitÃł
    -0.27
     Knicks
    -0.27
    POSITIVE LOGITS
    Ū
    0.28
    .yang
    0.27
    [js
    0.25
     anomal
    0.23
    _codigo
    0.23
    ç½ij约
    0.22
    ');?>↵
    0.21
    #${
    0.21
    ǧ
    0.21
    elsif
    0.21
    Activations Density 2.277%

    No Known Activations