© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28078
    Prev
    Next
    INDEX
    Explanations

    colonies and settlers

    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
     Napoleon
    -0.11
     Tibetan
    -0.11
     rej
    -0.10
     parade
    -0.09
     Toledo
    -0.09
     Kaiser
    -0.09
     skies
    -0.09
     Italy
    -0.09
    asio
    -0.09
     Vend
    -0.09
    POSITIVE LOGITS
     settlers
    0.38
     colony
    0.36
     colon
    0.33
     sett
    0.32
     Colony
    0.32
     colonial
    0.31
     colonization
    0.31
     settlement
    0.30
     Colon
    0.30
     colonies
    0.29
    Activations Density 0.567%

    No Known Activations