© 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. 111785
    Prev
    Next
    INDEX
    Explanations

    war and fighting

    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
     idiots
    -0.10
    IDI
    -0.10
     idi
    -0.10
     Samar
    -0.09
     mold
    -0.09
     Polic
    -0.09
     gravid
    -0.09
     racist
    -0.09
     Oversight
    -0.09
     Venezuel
    -0.08
    POSITIVE LOGITS
     battle
    0.33
     attack
    0.32
     warfare
    0.30
     battlefield
    0.30
     battleground
    0.30
     battles
    0.28
     attacking
    0.27
     conquered
    0.26
     enemy
    0.26
     war
    0.26
    Activations Density 0.192%

    No Known Activations