© 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. 8068
    Prev
    Next
    INDEX
    Explanations

    Roman and classical history

    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
     Cleveland
    -0.09
    _blue
    -0.08
     Worksheets
    -0.08
     gra
    -0.08
     Graz
    -0.07
     blue
    -0.07
    alach
    -0.07
     Chips
    -0.07
     kicks
    -0.07
    .blue
    -0.07
    POSITIVE LOGITS
     Rome
    0.16
     Romans
    0.16
     Roman
    0.15
     Medieval
    0.13
     medieval
    0.13
     mammals
    0.12
    Roman
    0.12
     Gothic
    0.11
     afterward
    0.11
     subsequent
    0.11
    Activations Density 0.032%

    No Known Activations