© 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. 7576
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    parentheses around function arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    comma followed by len

    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
     each
    -0.08
    .position
    -0.04
    ique
    -0.04
    ×
    -0.03
    Ø
    -0.03
    ä
    -0.03
    ã
    -0.03
    87
    -0.03
    ç
    -0.03
    é
    -0.03
    POSITIVE LOGITS
    qrt
    0.07
     abs
    0.05
    ab
    0.05
    .
    0.03
     elif
    0.03
     if
    0.03
    .split
    0.02
     del
    0.02
    _set
    0.02
    split
    0.02
    Activations Density 63.515%

    No Known Activations