© 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. 1822
    Prev
    Next
    INDEX
    Explanations

    function definition or call arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    dictionary keys or list indices

    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
    valid
    -0.09
    sible
    -0.08
    ab
    -0.08
     shortest
    -0.07
    (n
    -0.05
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    POSITIVE LOGITS
    .name
    0.21
    .id
    0.21
    _idx
    0.17
    dex
    0.17
    _index
    0.10
     op
    0.10
    <|
    0.08
    [-
    0.06
    St
    0.06
    key
    0.05
    Activations Density 99.994%

    No Known Activations