© 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. 27
    Prev
    Next
    INDEX
    Explanations

    filter or configure method calls

    python-code · gemini-2.5-flash-lite

    filter text (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
    No
    -0.38
     lab
    -0.37
     bre
    -0.33
    Z
    -0.33
    J
    -0.32
     heap
    -0.30
    .time
    -0.29
    En
    -0.29
     Value
    -0.28
     colle
    -0.27
    POSITIVE LOGITS
     or
    0.19
    _map
    0.14
    _to
    0.13
    _re
    0.10
    _st
    0.09
    _de
    0.09
    _n
    0.09
    '
    0.00
    !
    0.00
    #
    0.00
    Activations Density 100.000%

    No Known Activations