© 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. 50658
    Prev
    Next
    INDEX
    Explanations

    surprise or mild exasperation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ok
    -0.12
     Wow
    -0.11
    Ok
    -0.10
    Wow
    -0.10
    _ok
    -0.10
     Ok
    -0.10
    wow
    -0.09
     dann
    -0.09
    okies
    -0.09
     chir
    -0.09
    POSITIVE LOGITS
    enet
    0.09
     irony
    0.09
     Lonely
    0.09
    ixer
    0.08
     clever
    0.08
    spinner
    0.08
     briefed
    0.08
     bitter
    0.08
     Barg
    0.08
     Pornhub
    0.08
    Activations Density 0.009%

    No Known Activations