© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 1645
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .co combinations

    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
    Negative Logits
     top
    -0.01
     "__
    -0.01
    ag
    -0.01
    lif
    -0.01
    ¿
    -0.01
    _graph
    -0.00
    iz
    -0.00
     ad
    -0.00
    .ch
    -0.00
     index
    -0.00
    POSITIVE LOGITS
     un
    0.04
    _un
    0.04
    un
    0.04
    ce
    0.03
    ces
    0.03
    cies
    0.02
    anage
    0.02
    cy
    0.02
    xF
    0.01
    are
    0.01
    Activations Density 61.317%

    No Known Activations