© 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. 28317
    Prev
    Next
    INDEX
    Explanations

    fight or war

    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
     squir
    -0.10
     blackmail
    -0.10
     Elvis
    -0.09
    Probe
    -0.09
     scandal
    -0.09
     scandals
    -0.09
    WG
    -0.08
     Ashton
    -0.08
    istration
    -0.08
     scams
    -0.08
    POSITIVE LOGITS
     fighting
    0.61
     battle
    0.60
     fight
    0.57
     combat
    0.56
     battlefield
    0.53
     battles
    0.52
     fights
    0.50
    fight
    0.48
     fought
    0.47
    battle
    0.46
    Activations Density 0.682%

    No Known Activations