© 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. 8211
    Prev
    Next
    INDEX
    Explanations

    military service

    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
     stump
    -0.09
     lobbyist
    -0.09
     Lobby
    -0.09
     councillors
    -0.09
     portal
    -0.08
     Kann
    -0.08
     clinic
    -0.08
     Fuel
    -0.08
     superintendent
    -0.08
     fuel
    -0.08
    POSITIVE LOGITS
     army
    0.35
     navy
    0.32
     Army
    0.31
     military
    0.30
     Navy
    0.27
    Army
    0.25
     Military
    0.23
     armies
    0.22
    ilitary
    0.22
     Marines
    0.21
    Activations Density 0.953%

    No Known Activations