© 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. 117404
    Prev
    Next
    INDEX
    Explanations

    surprise, unexpected, or negative outcomes

    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
    ilet
    -0.10
     Tub
    -0.10
     Rhe
    -0.09
     automat
    -0.09
    paren
    -0.09
     tub
    -0.08
    Paragraph
    -0.08
     buoy
    -0.08
     Tul
    -0.08
    usic
    -0.08
    POSITIVE LOGITS
     surprised
    0.24
     surprise
    0.24
     surprising
    0.22
     surprises
    0.21
     unsur
    0.19
     Surprise
    0.18
     surpr
    0.15
     shocked
    0.15
     astonished
    0.12
     unexpected
    0.12
    Activations Density 0.095%

    No Known Activations