© 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. MLP
    9. 6-MLP
    11. 3655
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    isalpha or isalnum check

    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
    >
    -0.06
    quence
    -0.04
    quen
    -0.04
    ×
    -0.03
    gment
    -0.03
    Ø
    -0.03
     found
    -0.03
    ä
    -0.03
    ã
    -0.03
    arch
    -0.03
    POSITIVE LOGITS
    4
    0.12
    500
    0.09
    100
    0.07
    10
    0.06
    90
    0.05
    50
    0.05
    200
    0.05
    6
    0.05
    40
    0.04
    20
    0.04
    Activations Density 21.064%

    No Known Activations