© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 104
    Prev
    Next
    INDEX
    Explanations

    string generation or constants

    python-code · gemini-2.5-flash-lite

    string.ascii_ (letters, digits, uppercase, lowercase) (negative activations)

    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
    ³
    -0.33
    ighb
    -0.27
    54
    -0.22
    55
    -0.16
    56
    -0.15
    57
    -0.13
    52
    -0.12
    ´
    -0.10
    58
    -0.08
    51
    -0.06
    POSITIVE LOGITS
     inter
    0.20
    _inter
    0.20
    ĩ
    0.11
     instruction
    0.10
    (in
    0.09
    in
    0.08
     instructions
    0.08
     In
    0.08
    .in
    0.08
    88
    0.07
    Activations Density 100.000%

    No Known Activations