© 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. 50775
    Prev
    Next
    INDEX
    Explanations

    contrasting groups of people

    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
     Either
    -0.09
     behaved
    -0.08
    ined
    -0.08
    ario
    -0.08
     unanimously
    -0.07
     either
    -0.07
     reverted
    -0.07
     alternate
    -0.07
    inder
    -0.07
     assurances
    -0.07
    POSITIVE LOGITS
     humans
    0.16
     ours
    0.16
     Europeans
    0.16
     Americans
    0.16
     whereas
    0.15
     Whereas
    0.15
     theirs
    0.14
    Americans
    0.14
     Asians
    0.14
     unlike
    0.13
    Activations Density 0.243%

    No Known Activations