© 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. 29553
    Prev
    Next
    INDEX
    Explanations

    adverse/favorable outcomes and effects

    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
     positive
    -0.13
     Positive
    -0.11
     positives
    -0.11
     positivity
    -0.10
     optimism
    -0.10
    Positive
    -0.10
    akin
    -0.09
    positive
    -0.09
     positively
    -0.09
    ogle
    -0.09
    POSITIVE LOGITS
     reaction
    0.15
     surprise
    0.15
     surprised
    0.15
     surprises
    0.14
     attitude
    0.13
     reactions
    0.13
     verdict
    0.13
     sentiments
    0.13
     Reaction
    0.13
     outcome
    0.13
    Activations Density 0.272%

    No Known Activations