© 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. 2175
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string.ascii_ lower or uppercase

    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
     whi
    -0.05
    is
    -0.04
    we
    -0.04
    Y
    -0.04
    ru
    -0.03
    ¾
    -0.03
    _m
    -0.02
    ts
    -0.02
    1
    -0.02
    ir
    -0.02
    POSITIVE LOGITS
    c
    0.09
    ig
    0.08
    ci
    0.07
    ati
    0.04
    e
    0.04
    ail
    0.04
    Ģ
    0.04
    set
    0.04
    inary
    0.04
    str
    0.04
    Activations Density 45.819%

    No Known Activations