© 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. 1115
    Prev
    Next
    INDEX
    Explanations

    for loop iteration (negative activations)

    python-code · gemini-2.5-flash-lite

    dict.fromkeys, .keys, .items call

    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
    _cells
    -0.40
    _rate
    -0.37
    _level
    -0.28
    .position
    -0.25
    _items
    -0.24
     size
    -0.23
    _comp
    -0.22
    _pairs
    -0.20
    _item
    -0.19
    resh
    -0.18
    POSITIVE LOGITS
     ex
    0.10
     visited
    0.09
    _data
    0.08
    56
    0.06
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    Activations Density 97.342%

    No Known Activations