© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1981
    Prev
    Next
    INDEX
    Explanations

    assignment before colon (negative activations)

    python-code · gemini-2.5-flash-lite

    dot followed by method call

    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
     q
    -0.31
    q
    -0.24
    gs
    -0.16
     r
    -0.16
    .d
    -0.14
    Q
    -0.13
     id
    -0.09
     dist
    -0.09
    X
    -0.07
     g
    -0.06
    POSITIVE LOGITS
    ffe
    0.23
    imum
    0.17
    adjac
    0.13
    li
    0.10
     spe
    0.09
    ing
    0.06
    and
    0.06
     co
    0.05
        ↵
    0.04
    S
    0.04
    Activations Density 100.000%

    No Known Activations