© 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. 5016
    Prev
    Next
    INDEX
    Explanations

    divorce and widowhood events

    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
     Childhood
    -0.11
     synthes
    -0.10
     childhood
    -0.10
    486
    -0.10
     ROT
    -0.09
    ogl
    -0.09
     Alta
    -0.09
    anas
    -0.09
    gam
    -0.09
     apologize
    -0.09
    POSITIVE LOGITS
     remar
    0.30
     widow
    0.22
     wid
    0.22
     divorced
    0.21
     divorce
    0.20
     Widow
    0.20
     rebuilding
    0.17
     single
    0.16
    /single
    0.16
     rebound
    0.16
    Activations Density 0.130%

    No Known Activations