© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    random.randrange

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    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
    Negative Logits
     plt
    -0.06
    eight
    -0.04
    atus
    -0.04
    itness
    -0.04
    weight
    -0.04
     Value
    -0.03
    gree
    -0.03
    _score
    -0.03
    _length
    -0.03
     height
    -0.03
    Positive Logits
    (len
    0.10
     len
    0.07
    len
    0.07
     for
    0.06
    (N
    0.05
     any
    0.05
    for
    0.05
    (n
    0.05
     ""
    0.05
    join
    0.04
    Activations Density 58.354%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `replace(` or `while` or `*` or literal `6` (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment to variable

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    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
    Negative Logits
    vailable
    -0.03
    sed
    -0.03
    ilename
    -0.03
    mit
    -0.02
    ^
    -0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Positive Logits
    pro
    0.02
     l
    0.02
     g
    0.01
     G
    0.01
    ul
    0.01
    3
    0.01
    .
    0.01
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 59.092%

    No Known Activations