© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113827
    Prev
    Next
    INDEX
    Explanations

    imperial and war concepts

    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
     MEN
    -0.10
     Rena
    -0.09
     Tobias
    -0.09
     mens
    -0.09
     opi
    -0.08
     raspberry
    -0.08
     DMA
    -0.08
    utters
    -0.08
    Legacy
    -0.08
    айд
    -0.08
    POSITIVE LOGITS
     demon
    0.12
     imperial
    0.12
     armies
    0.11
     battles
    0.11
     generals
    0.11
     naval
    0.10
     submarine
    0.10
     Emperor
    0.10
     fleet
    0.10
     emperor
    0.10
    Activations Density 0.016%

    No Known Activations