© 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. 14
    Prev
    Next
    INDEX
    Explanations

    number literal 500

    python-code · gemini-2.5-flash-lite

    attribute access `.p` (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
    idth
    -0.27
    alue
    -0.26
    reshold
    -0.25
    fset
    -0.24
    gth
    -0.22
    _size
    -0.22
    _rate
    -0.21
    dex
    -0.21
    riority
    -0.20
    size
    -0.19
    POSITIVE LOGITS
    ai
    0.12
     lon
    0.10
     test
    0.09
    _dist
    0.09
    que
    0.08
     del
    0.07
    we
    0.06
    test
    0.06
    tic
    0.06
     optim
    0.06
    Activations Density 100.000%

    No Known Activations