© 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. 606
    Prev
    Next
    INDEX
    Explanations

    import statement (negative activations)

    python-code · gemini-2.5-flash-lite

    urllib.request or def keyword

    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
    (N
    -0.26
    qrt
    -0.22
    (map
    -0.17
    (len
    -0.15
     x
    -0.12
     ele
    -0.11
    (n
    -0.10
    [i
    -0.09
     Tuple
    -0.06
    )
    -0.03
    POSITIVE LOGITS
    atus
    0.21
    ost
    0.19
     conne
    0.17
    _for
    0.17
    200
    0.15
     spe
    0.11
     re
    0.10
    ).
    0.09
    form
    0.09
    ut
    0.09
    Activations Density 100.000%

    No Known Activations