© 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. 270
    Prev
    Next
    INDEX
    Explanations

    dict keys or values

    python-code · gemini-2.5-flash-lite

    pass keyword or ellipsis placeholder (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
     log
    -0.21
    ..
    -0.17
     bre
    -0.15
    ction
    -0.10
    ...
    -0.09
     he
    -0.08
    ic
    -0.08
     algorithm
    -0.07
     based
    -0.07
    ')↵
    -0.06
    POSITIVE LOGITS
    .keys
    0.28
    .items
    0.19
    ].
    0.15
    .values
    0.14
    .strip
    0.08
    .↵↵
    0.08
     b
    0.03
     se
    0.03
    ↵↵
    0.02
    '
    0.00
    Activations Density 100.000%

    No Known Activations