© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29594
    Prev
    Next
    INDEX
    Explanations

    diplomatic exchanges and agreements

    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
    Negative Logits
     classmates
    -0.11
     roommate
    -0.11
     chores
    -0.10
     goof
    -0.09
     centrally
    -0.09
     Rookie
    -0.09
     Homework
    -0.09
     rookies
    -0.09
     Prep
    -0.09
     teammates
    -0.09
    POSITIVE LOGITS
     hospitality
    0.19
     representatives
    0.19
     diplom
    0.18
     negotiations
    0.17
     negotiation
    0.17
     negotiating
    0.17
     envoy
    0.16
     negoci
    0.16
     politely
    0.16
     delegation
    0.16
    Activations Density 0.106%

    No Known Activations