© 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. 115715
    Prev
    Next
    INDEX
    Explanations

    **during pregnancy**

    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
     Ether
    -0.09
    enting
    -0.08
    italic
    -0.08
     eof
    -0.08
     interle
    -0.08
    iras
    -0.08
    dden
    -0.08
    clide
    -0.08
    annie
    -0.08
    agged
    -0.08
    POSITIVE LOGITS
     pdf
    0.12
    formula
    0.10
     gratuit
    0.09
     CENTER
    0.09
    oppers
    0.08
     opin
    0.08
     gif
    0.08
     apk
    0.08
     uk
    0.08
     usa
    0.08
    Activations Density 0.023%

    No Known Activations