© 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. 7698
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    random.seed or repeat parameter

    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
     other
    -0.10
    other
    -0.08
     __
    -0.08
    ep
    -0.06
    __(
    -0.06
    ent
    -0.05
    ents
    -0.05
    ency
    -0.05
    le
    -0.04
    able
    -0.03
    POSITIVE LOGITS
    p
    0.09
    co
    0.06
    e
    0.06
    point
    0.05
    i
    0.05
     p
    0.05
     lon
    0.05
    lit
    0.04
    ld
    0.04
     L
    0.04
    Activations Density 1.062%

    No Known Activations