© 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. 789
    Prev
    Next
    INDEX
    Explanations

    emailed, celsius, flagged (negative activations)

    python-code · gemini-2.5-flash-lite

    date, time, keras, loss, players

    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
    ge
    -0.20
    -0.17
    ore
    -0.15
    -0.13
    tile
    -0.13
    ¾
    -0.10
    lay
    -0.09
    -0.05
    _from
    -0.04
    '
    0.00
    POSITIVE LOGITS
    tier
    0.31
    cies
    0.27
    cy
    0.26
    gre
    0.18
    vent
    0.18
    _tree
    0.16
    ree
    0.16
    jects
    0.15
    ject
    0.15
    68
    0.14
    Activations Density 100.000%

    No Known Activations