© 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. 1672
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    keyword `import` or `from`

    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
    >
    -0.07
    ess
    -0.05
    ="
    -0.04
    ='
    -0.04
    <
    -0.03
    .
    -0.03
    ffic
    -0.03
    =
    -0.03
    vers
    -0.03
    !
    -0.03
    POSITIVE LOGITS
    Ĵ
    0.06
    (he
    0.06
    _he
    0.06
    H
    0.05
     height
    0.05
     heap
    0.05
     H
    0.05
    _height
    0.05
    .he
    0.05
     heuristic
    0.05
    Activations Density 1.810%

    No Known Activations