© 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. Residual Stream
    9. 7-RESID
    11. 398
    Prev
    Next
    INDEX
    Explanations

    parts of words

    python-code · gemini-2.5-flash-lite

    part of string.punctuation (negative activations)

    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
    hip
    -0.24
    _from
    -0.17
    un
    -0.11
    ward
    -0.10
     from
    -0.05
     a
    -0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    POSITIVE LOGITS
    u
    0.27
    ual
    0.21
    ure
    0.18
    ©
    0.17
    ut
    0.15
    utation
    0.15
     u
    0.14
    uc
    0.13
    69
    0.12
    U
    0.09
    Activations Density 100.000%

    No Known Activations