© 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. 7970
    Prev
    Next
    INDEX
    Explanations

    Australian places and achievements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    £
    -0.20
     (£
    -0.20
     £
    -0.19
    .uk
    -0.17
     NHS
    -0.17
     UK
    -0.16
     county
    -0.15
     rooted
    -0.15
    BBC
    -0.15
     BBC
    -0.14
    POSITIVE LOGITS
     Australian
    0.45
     Queensland
    0.42
     Australia
    0.42
    Australian
    0.40
     Australians
    0.40
     Brisbane
    0.40
     Melbourne
    0.39
     NSW
    0.39
     Canberra
    0.39
     Aussie
    0.38
    Activations Density 3.003%

    No Known Activations