© 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. MLP
    9. 6-MLP
    11. 4548
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment from list comprehension

    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
    W
    -0.05
     W
    -0.04
    ffe
    -0.04
    H
    -0.03
     H
    -0.03
    imum
    -0.03
    29
    -0.02
    ross
    -0.02
    adjac
    -0.02
    S
    -0.02
    POSITIVE LOGITS
     q
    0.05
    er
    0.04
    q
    0.04
    ers
    0.03
     found
    0.03
    ist
    0.03
    70
    0.03
    heck
    0.03
    is
    0.03
     check
    0.03
    Activations Density 15.196%

    No Known Activations