© 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. 88850
    Prev
    Next
    INDEX
    Explanations

    capital cities and capitols

    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
    cel
    -0.09
    ManagerInterface
    -0.08
     regenerate
    -0.08
     expansive
    -0.08
    ometer
    -0.08
     medium
    -0.08
     Nina
    -0.08
    Manifest
    -0.08
     Meteor
    -0.08
    board
    -0.08
    POSITIVE LOGITS
     Canberra
    0.14
     Capitals
    0.13
     Capitol
    0.13
     DC
    0.12
     Capital
    0.12
     Ottawa
    0.11
     Rome
    0.11
     Washington
    0.11
     lobbyist
    0.10
    isl
    0.10
    Activations Density 0.208%

    No Known Activations