© 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. 25131
    Prev
    Next
    INDEX
    Explanations

    foreigners and immigrants

    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
    rei
    -0.09
     Blessed
    -0.09
     Tod
    -0.09
     blessed
    -0.09
    üt
    -0.09
    aea
    -0.08
     Davidson
    -0.08
     ASA
    -0.08
     conjug
    -0.08
     forwarding
    -0.08
    POSITIVE LOGITS
     unfamiliar
    0.15
    /local
    0.15
    /native
    0.13
    /new
    0.12
    /non
    0.12
     outsider
    0.12
     arriving
    0.11
    /custom
    0.11
     foreigners
    0.11
     arrivals
    0.11
    Activations Density 0.300%

    No Known Activations