© 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. 34002
    Prev
    Next
    INDEX
    Explanations

    city and province names

    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
     city
    -0.25
    city
    -0.21
     cities
    -0.21
     CITY
    -0.21
     City
    -0.21
     town
    -0.20
    -city
    -0.20
    City
    -0.20
    åŁİ
    -0.19
     downtown
    -0.18
    POSITIVE LOGITS
     province
    0.17
     Province
    0.14
     country
    0.13
    province
    0.13
     Alabama
    0.12
    Country
    0.12
    country
    0.12
     Maharashtra
    0.12
     provinces
    0.12
     Alberta
    0.11
    Activations Density 0.934%

    No Known Activations