© 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. 111372
    Prev
    Next
    INDEX
    Explanations

    medium, light, heavy

    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
     Ves
    -0.11
     Filed
    -0.10
     prise
    -0.10
     chim
    -0.09
     dissolution
    -0.09
    isco
    -0.09
    ufs
    -0.09
    -pane
    -0.09
     horm
    -0.09
    mond
    -0.09
    POSITIVE LOGITS
     mediums
    0.12
     lightweight
    0.11
     heavyweight
    0.11
     weights
    0.10
     stocked
    0.10
     medium
    0.10
     fabrics
    0.09
     Jenn
    0.09
    ito
    0.09
     Medium
    0.09
    Activations Density 0.004%

    No Known Activations