© 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. 1063
    Prev
    Next
    INDEX
    Explanations

    math.radians or atan2 arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    from collections import

    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
    an
    -0.27
    ax
    -0.12
     ra
    -0.10
    q
    -0.09
    ut
    -0.07
    i
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    POSITIVE LOGITS
    ry
    0.32
    con
    0.23
    iti
    0.22
    ary
    0.19
    ad
    0.10
     []↵
    0.08
    ari
    0.07
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 99.519%

    No Known Activations