© 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. 25679
    Prev
    Next
    INDEX
    Explanations

    COVID-19 variants and timeline

    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
     annually
    -0.11
     boyc
    -0.11
     Terrorism
    -0.11
     decades
    -0.11
    terrorism
    -0.10
     yearly
    -0.10
    cancelled
    -0.10
     Hazel
    -0.10
     terrorism
    -0.10
     traditionally
    -0.10
    POSITIVE LOGITS
    erna
    0.14
     rollout
    0.12
    variant
    0.12
     timeline
    0.12
     variant
    0.11
     Delta
    0.11
     Om
    0.11
     delta
    0.10
     pace
    0.10
     tracker
    0.10
    Activations Density 1.160%

    No Known Activations