© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1081
    Prev
    Next
    INDEX
    Explanations

    format or time string (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute access `.speed`

    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
    fs
    -0.27
    ¤
    -0.26
    ft
    -0.18
     final
    -0.18
    fe
    -0.18
    f
    -0.18
    xf
    -0.16
     file
    -0.16
    fi
    -0.15
    ffe
    -0.14
    POSITIVE LOGITS
    uzz
    0.21
    xb
    0.14
    xa
    0.13
    uzzle
    0.12
    old
    0.10
    out
    0.07
    xc
    0.07
    new
    0.05
    _n
    0.05
     new
    0.02
    Activations Density 99.206%

    No Known Activations