© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1649
    Prev
    Next
    INDEX
    Explanations

    `re.findall` or `self.` attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    .join or .number or column

    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
     col
    -0.17
    ors
    -0.14
    all
    -0.13
     num
    -0.11
     q
    -0.08
    _data
    -0.07
    en
    -0.06
     step
    -0.06
    f
    -0.05
    '
    0.00
    POSITIVE LOGITS
    duct
    0.22
     column
    0.20
     queue
    0.17
    quen
    0.17
    zero
    0.16
    enden
    0.16
     number
    0.09
    iz
    0.08
    _info
    0.06
    _v
    0.05
    Activations Density 94.866%

    No Known Activations