© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117540
    Prev
    Next
    INDEX
    Explanations

    marry, marriage, wedding

    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
    Negative Logits
     Bust
    -0.09
     Esper
    -0.09
     Lantern
    -0.08
     Indones
    -0.08
     Corps
    -0.08
    -interest
    -0.08
     lantern
    -0.08
     corps
    -0.08
     Karn
    -0.08
     ac
    -0.08
    POSITIVE LOGITS
     marriage
    0.48
     marry
    0.42
     Marriage
    0.40
     married
    0.36
     marrying
    0.36
     wedding
    0.32
     mariage
    0.32
     marriages
    0.30
    married
    0.27
     Wedding
    0.26
    Activations Density 0.101%

    No Known Activations