© 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. 29320
    Prev
    Next
    INDEX
    Explanations

    [country/state] of [country/state]

    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
    fox
    -0.10
     continents
    -0.09
     intl
    -0.09
     strut
    -0.09
     Oslo
    -0.09
     asia
    -0.09
     museums
    -0.09
     politicians
    -0.09
     observ
    -0.09
     Asia
    -0.09
    POSITIVE LOGITS
     Kingdom
    0.22
     Republic
    0.20
     kingdom
    0.18
     kingdoms
    0.15
     Empire
    0.15
     United
    0.15
     republic
    0.14
    Republic
    0.14
     united
    0.14
     empire
    0.14
    Activations Density 1.279%

    No Known Activations