© 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
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. MLP
    5. 6-MLP
    6. 2632
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string argument separator

    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
     each
    -0.08
    ique
    -0.04
     whe
    -0.02
     all
    -0.02
    endoftext
    -0.02
     Create
    -0.02
    for
    -0.01
     {}↵
    -0.01
     results
    -0.01
    ."""↵
    -0.01
    POSITIVE LOGITS
    qrt
    0.07
     abs
    0.05
     '#
    0.05
    ="
    0.05
     '.
    0.05
     '
    0.05
     "
    0.04
    ='
    0.04
     ".
    0.04
    ab
    0.04
    Activations Density 67.109%

    No Known Activations