© 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. 117381
    Prev
    Next
    INDEX
    Explanations

    official positions and roles

    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
     Manufacturers
    -0.13
     Suppliers
    -0.13
     vendors
    -0.13
     farmers
    -0.12
     Governors
    -0.11
     Contractors
    -0.11
     Farmers
    -0.11
     Manufacturer
    -0.11
     suppliers
    -0.11
     Sellers
    -0.11
    POSITIVE LOGITS
     representative
    0.25
     representatives
    0.19
     senior
    0.17
     manager
    0.15
     representa
    0.15
     assistant
    0.14
     spokes
    0.13
     handler
    0.13
     emiss
    0.13
     Representative
    0.13
    Activations Density 0.300%

    No Known Activations