© 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. 70
    Prev
    Next
    INDEX
    Explanations

    is empty or attribute name

    python-code · gemini-2.5-flash-lite

    self.attribute access (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
    uples
    -0.27
    ilities
    -0.25
    inations
    -0.23
     instructions
    -0.23
    _locations
    -0.22
    asks
    -0.21
    _pairs
    -0.21
    endencies
    -0.21
     locations
    -0.21
    keys
    -0.21
    POSITIVE LOGITS
    ycle
    0.06
     loc
    0.05
     step
    0.04
    ustom
    0.04
    cy
    0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Activations Density 100.000%

    No Known Activations