© 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. 390
    Prev
    Next
    INDEX
    Explanations

    'str' literal strings

    python-code · gemini-2.5-flash-lite

    hexdigest() (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
    "
    -0.23
    '
    -0.21
    "{
    -0.19
    '.
    -0.11
    's
    -0.06
    .randint
    -0.04
     variables
    -0.04
    {
    -0.04
    .index
    -0.03
    #
    0.00
    POSITIVE LOGITS
     ",
    0.10
     or
    0.03
    .b
    0.03
     num
    0.02
    #
    0.00
    +
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    Activations Density 99.998%

    No Known Activations