© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1428
    Prev
    Next
    INDEX
    Explanations

    string literal enclosed in parentheses (negative activations)

    python-code · gemini-2.5-flash-lite

    decorator syntax / import statements

    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
    -0.35
    ique
    -0.18
     whe
    -0.11
     all
    -0.08
     Create
    -0.07
    for
    -0.06
     {}↵
    -0.06
     results
    -0.05
     [(
    -0.05
     un
    -0.04
    POSITIVE LOGITS
    qrt
    0.31
     abs
    0.24
    ab
    0.21
     elif
    0.13
     if
    0.12
     del
    0.11
     distance
    0.09
    class
    0.07
     math
    0.07
     In
    0.06
    Activations Density 100.000%

    No Known Activations