© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1815
    Prev
    Next
    INDEX
    Explanations

    index variable in loops and conditions (negative activations)

    python-code · gemini-2.5-flash-lite

    heapq.heappush

    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
     hi
    -0.10
    hi
    -0.07
    _h
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    !
    0.00
    POSITIVE LOGITS
     he
    0.26
    _he
    0.21
    .heapp
    0.20
    tail
    0.20
    (he
    0.20
    he
    0.18
    .he
    0.14
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 100.000%

    No Known Activations