© 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. 220
    Prev
    Next
    INDEX
    Explanations

    most_common method arguments

    python-code · gemini-2.5-flash-lite

    compiling code (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
    d
    -0.28
    che
    -0.23
    u
    -0.14
    red
    -0.13
    ed
    -0.10
    it
    -0.09
    un
    -0.08
    p
    -0.04
    ti
    -0.04
    n
    -0.03
    POSITIVE LOGITS
    act
    0.23
    vi
    0.15
    def
    0.13
    w
    0.09
    one
    0.08
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Activations Density 93.186%

    No Known Activations