© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4929
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    import aliasing

    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
    (len
    -0.09
     len
    -0.06
    len
    -0.06
     [(
    -0.06
     label
    -0.06
     comb
    -0.06
     []↵↵
    -0.05
    [(
    -0.05
     []↵
    -0.05
     {}↵↵
    -0.04
    POSITIVE LOGITS
    ())
    0.05
    ative
    0.04
    itial
    0.04
    (),
    0.04
    ())↵
    0.04
    ()
    0.04
    q
    0.04
    ().
    0.04
    ()↵
    0.04
    ()↵↵
    0.04
    Activations Density 84.115%

    No Known Activations