© 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. Residual Stream
    9. 7-RESID
    11. 1224
    Prev
    Next
    INDEX
    Explanations

    self.number or self.column (negative activations)

    python-code · gemini-2.5-flash-lite

    self.radius attribute

    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
    -0.25
    rib
    -0.24
    umn
    -0.23
    ber
    -0.22
    ulation
    -0.21
    µ
    -0.20
    ion
    -0.20
    atri
    -0.19
     each
    -0.18
    ink
    -0.17
    POSITIVE LOGITS
     whe
    0.16
    us
    0.14
     step
    0.10
    of
    0.10
     pro
    0.10
    is
    0.10
    idth
    0.10
    _in
    0.10
    he
    0.09
    55
    0.09
    Activations Density 100.000%

    No Known Activations