© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1152
    Prev
    Next
    INDEX
    Explanations

    hexdigest or exception (negative activations)

    python-code · gemini-2.5-flash-lite

    circumference or temperature variables

    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
    x
    -0.16
    di
    -0.15
    50
    -0.13
    gment
    -0.08
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    POSITIVE LOGITS
    ulate
    0.32
    ulation
    0.29
    ul
    0.26
    rue
    0.16
    il
    0.15
    les
    0.14
    zero
    0.13
    array
    0.11
    si
    0.10
    ry
    0.10
    Activations Density 99.478%

    No Known Activations