© 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. 91820
    Prev
    Next
    INDEX
    Explanations

    postpartum period

    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
     sal
    -0.09
     cancelling
    -0.09
     revoked
    -0.09
     Tomorrow
    -0.09
     Dick
    -0.09
     staging
    -0.08
    YLE
    -0.08
     procur
    -0.08
    acht
    -0.08
     Gord
    -0.08
    POSITIVE LOGITS
     post
    0.30
     breastfeeding
    0.30
     maternity
    0.25
     Post
    0.23
    post
    0.22
     lact
    0.22
     baby
    0.21
     mothers
    0.21
    Post
    0.20
     childbirth
    0.20
    Activations Density 0.263%

    No Known Activations