© 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. 3239
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    constructor arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    variable name ending in `_counts`

    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
    09
    -0.02
    08
    -0.02
    07
    -0.02
     rows
    -0.01
    dition
    -0.01
     col
    -0.01
    mple
    -0.01
    _nodes
    -0.01
    init
    -0.01
    The
    -0.01
    POSITIVE LOGITS
    .keys
    0.03
    ["
    0.03
    .values
    0.03
    ['
    0.02
    .items
    0.02
    2
    0.02
    [t
    0.02
     each
    0.02
    _to
    0.02
    (min
    0.02
    Activations Density 88.260%

    No Known Activations