© 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. 3412
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    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
     reconstruction
    -0.11
     Prev
    -0.10
     Marketplace
    -0.10
     prevailing
    -0.10
     recon
    -0.10
     perv
    -0.09
    dong
    -0.09
     Thorn
    -0.09
     Flyers
    -0.09
     Biz
    -0.09
    POSITIVE LOGITS
     Europe
    0.21
     world
    0.21
     worldwide
    0.19
    Europe
    0.16
     WORLD
    0.15
     Asia
    0.15
     europe
    0.15
     globally
    0.15
     Worldwide
    0.15
    /world
    0.14
    Activations Density 0.809%

    No Known Activations