© 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. 3472
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable method calls

    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
    anage
    -0.04
    olver
    -0.03
    uil
    -0.02
    ","
    -0.02
    ator
    -0.02
    .name
    -0.02
    .id
    -0.02
    tim
    -0.02
    xF
    -0.02
     nx
    -0.02
    POSITIVE LOGITS
    -
    0.03
     found
    0.03
    (str
    0.03
    _queue
    0.02
    ab
    0.02
     ele
    0.02
    rontier
    0.02
    ho
    0.02
     heap
    0.02
    queue
    0.02
    Activations Density 88.935%

    No Known Activations