© 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. 1900
    Prev
    Next
    INDEX
    Explanations

    accessing list/deque items with indices (negative activations)

    python-code · gemini-2.5-flash-lite

    is_empty method

    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
    _rate
    -0.27
    _li
    -0.20
    utation
    -0.19
    apac
    -0.16
    temp
    -0.14
    _matrix
    -0.13
    _capacity
    -0.13
    vai
    -0.13
    apacity
    -0.11
    _size
    -0.10
    POSITIVE LOGITS
    _valid
    0.26
     valid
    0.21
    uple
    0.19
    _pos
    0.15
    uples
    0.15
     best
    0.12
     int
    0.11
     id
    0.10
    ree
    0.10
    (i
    0.09
    Activations Density 99.946%

    No Known Activations