© 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. 87600
    Prev
    Next
    INDEX
    Explanations

    sudden emotional or physical events

    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
     slowly
    -0.12
     gradually
    -0.11
     progressively
    -0.11
     increasingly
    -0.10
     dangling
    -0.09
     Exist
    -0.09
     incess
    -0.09
     confronting
    -0.09
     Clayton
    -0.09
     exist
    -0.08
    POSITIVE LOGITS
     surge
    0.17
     burst
    0.15
     rush
    0.13
     sweep
    0.13
     accompanying
    0.13
     occurred
    0.12
     occurs
    0.12
     wash
    0.12
     sudden
    0.11
     followed
    0.11
    Activations Density 0.072%

    No Known Activations