© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1850
    Prev
    Next
    INDEX
    Explanations

    .re followed by reader (negative activations)

    python-code · gemini-2.5-flash-lite

    json.dumps or itertools.product arguments

    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
    e
    -0.31
    erson
    -0.29
    ct
    -0.06
    E
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    POSITIVE LOGITS
    sp
    0.17
    our
    0.16
    K
    0.15
    .e
    0.09
    ad
    0.06
    ra
    0.05
    ant
    0.05
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 98.111%

    No Known Activations