© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3266
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    dictionary key-value pairs (negative activations)

    python-code · gemini-2.5-flash-lite

    list elements

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etween
    -0.07
    .keys
    -0.06
    verage
    -0.05
    itness
    -0.05
    eight
    -0.05
    otal
    -0.05
    ffe
    -0.04
    weight
    -0.04
     Value
    -0.04
    )],↵
    -0.04
    POSITIVE LOGITS
    ('
    0.05
    ("
    0.05
     >
    0.05
    ([
    0.03
    vertices
    0.03
    Node
    0.03
     Node
    0.02
    team
    0.02
    ({
    0.02
    arg
    0.02
    Activations Density 76.675%

    No Known Activations