© 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. 7705
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    sys module usage

    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
    in
    -0.04
    out
    -0.03
    n
    -0.02
    ve
    -0.02
    p
    -0.02
    of
    -0.02
    co
    -0.02
     whe
    -0.02
    g
    -0.02
    st
    -0.02
    POSITIVE LOGITS
    ss
    0.04
     each
    0.04
    join
    0.03
    rib
    0.03
    umn
    0.03
    iz
    0.03
    um
    0.03
    .m
    0.03
    _of
    0.03
    ber
    0.03
    Activations Density 37.405%

    No Known Activations