© 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. 14485
    Prev
    Next
    INDEX
    Explanations

    dominance or ruling power

    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
     unfortunate
    -0.12
     unlucky
    -0.11
     responder
    -0.11
     sacrificed
    -0.10
     contestant
    -0.10
    Responder
    -0.10
    awan
    -0.10
     Trade
    -0.10
     kidnapped
    -0.10
    ì¶
    -0.10
    POSITIVE LOGITS
     superiority
    0.16
     supremacy
    0.14
     dominance
    0.13
     superior
    0.12
     empowered
    0.12
     dominant
    0.12
    -led
    0.12
     ruling
    0.11
     authority
    0.11
     commanding
    0.11
    Activations Density 0.011%

    No Known Activations