© 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. 7488
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    attribute balance

    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
    ®
    -0.06
    tive
    -0.04
    strip
    -0.04
    ts
    -0.03
    tes
    -0.03
    vailable
    -0.03
    t
    -0.03
    rib
    -0.02
    .co
    -0.02
    te
    -0.02
    POSITIVE LOGITS
    ance
    0.08
    >
    0.06
    ef
    0.06
    lines
    0.06
    ant
    0.05
     zip
    0.04
    an
    0.04
    ute
    0.04
    ].
    0.03
    _lines
    0.03
    Activations Density 88.028%

    No Known Activations