© 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. 7316
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .write followed by parenthesis

    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
     other
    -0.07
    text
    -0.06
    other
    -0.06
     __
    -0.06
    __(
    -0.04
     se
    -0.03
    raw
    -0.03
    age
    -0.03
     dist
    -0.02
     distances
    -0.02
    POSITIVE LOGITS
    over
    0.10
    ree
    0.07
    si
    0.05
    in
    0.04
    ill
    0.04
     th
    0.03
    on
    0.03
    ing
    0.03
    ol
    0.03
    as
    0.03
    Activations Density 13.477%

    No Known Activations