© 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. 3592
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    attribute assignment `f` =

    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
    ase
    -0.05
    ame
    -0.04
    ameters
    -0.04
    ats
    -0.04
    sp
    -0.03
    ate
    -0.03
    at
    -0.03
    ±
    -0.03
    ates
    -0.03
    ater
    -0.02
    POSITIVE LOGITS
    on
    0.05
    ig
    0.04
    ir
    0.03
    M
    0.03
    m
    0.03
    mple
    0.03
    ram
    0.03
    mo
    0.03
    mp
    0.02
    mm
    0.02
    Activations Density 13.616%

    No Known Activations