© 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. Residual Stream
    9. 7-RESID
    11. 103
    Prev
    Next
    INDEX
    Explanations

    parenthesis, .attribute, or def keyword

    python-code · gemini-2.5-flash-lite

    datetime module usage or exceptions (negative activations)

    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
    &
    0.00
    *
    0.00
    #
    0.00
    '
    0.00
    )
    0.00
    %
    0.00
    !
    0.00
    "
    0.00
    $
    0.00
    (
    0.00
    POSITIVE LOGITS
    ari
    0.40
    ateg
    0.35
    ary
    0.33
    hip
    0.29
    ust
    0.29
    ors
    0.27
    ure
    0.26
    sible
    0.25
    ef
    0.23
    od
    0.22
    Activations Density 100.000%

    No Known Activations