© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28213
    Prev
    Next
    INDEX
    Explanations

    py programming and crypto context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uzu
    -0.09
    :disable
    -0.09
     pole
    -0.09
     cloves
    -0.09
     poles
    -0.09
    pole
    -0.08
    weit
    -0.08
     sug
    -0.08
     pups
    -0.08
     resemble
    -0.08
    POSITIVE LOGITS
    /py
    0.22
     Py
    0.20
     py
    0.18
    (Py
    0.18
    Py
    0.16
     Django
    0.16
    .py
    0.16
     PY
    0.15
    (py
    0.15
    pyx
    0.14
    Activations Density 0.524%

    No Known Activations