© 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
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. Residual Stream
    5. 7-RESID
    6. 1890
    Prev
    Next
    INDEX
    Explanations

    comma followed by variable (negative activations)

    python-code · gemini-2.5-flash-lite

    is alnum or is alpha

    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
    _capacity
    -0.17
     car
    -0.14
    .c
    -0.13
    _c
    -0.13
     cities
    -0.12
     closest
    -0.11
    _length
    -0.11
     child
    -0.10
    c
    -0.09
     length
    -0.09
    POSITIVE LOGITS
    .co
    0.18
    _col
    0.18
     colle
    0.18
    col
    0.17
    co
    0.15
    _co
    0.15
     col
    0.14
    _comp
    0.14
     comb
    0.14
    _counts
    0.14
    Activations Density 100.000%

    No Known Activations