© 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. MLP
    9. 6-MLP
    11. 7039
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    len followed by parenthesis

    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
    join
    -0.04
     found
    -0.04
    prese
    -0.03
    alculate
    -0.02
    <extra_output_id:2047>
    -0.02
    lable
    -0.02
     find
    -0.02
    000
    -0.02
    enerate
    -0.02
     calculate
    -0.02
    POSITIVE LOGITS
     queue
    0.02
     heapq
    0.02
    _data
    0.02
    _input
    0.01
     continue
    0.01
     stack
    0.01
     open
    0.01
     he
    0.01
     q
    0.01
     data
    0.01
    Activations Density 98.750%

    No Known Activations