© 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. 1179
    Prev
    Next
    INDEX
    Explanations

    isalpha, isalnum, isof, isupper (negative activations)

    python-code · gemini-2.5-flash-lite

    string literal content

    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
    jk
    -0.18
    ce
    -0.11
    te
    -0.09
    lo
    -0.09
    se
    -0.08
    ter
    -0.05
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    POSITIVE LOGITS
    ating
    0.26
    apping
    0.26
    v
    0.14
    iz
    0.13
    ut
    0.13
    ing
    0.12
    l
    0.07
    ation
    0.06
    '
    0.00
    #
    0.00
    Activations Density 88.800%

    No Known Activations