© 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. 1638
    Prev
    Next
    INDEX
    Explanations

    isalpha string method (negative activations)

    python-code · gemini-2.5-flash-lite

    .in followed by sert

    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
     representing
    -0.17
     between
    -0.13
     heuristic
    -0.13
    [(
    -0.11
    ['
    -0.11
    ["
    -0.10
    .set
    -0.09
     weights
    -0.09
    .add
    -0.07
    add
    -0.06
    POSITIVE LOGITS
    ron
    0.31
     heap
    0.29
     heapq
    0.27
    .pop
    0.22
    queue
    0.19
    left
    0.18
    orted
    0.18
    erge
    0.17
     sorted
    0.17
     right
    0.15
    Activations Density 100.000%

    No Known Activations