© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116063
    Prev
    Next
    INDEX
    Explanations

    by surprise

    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
     bounded
    -0.10
    isch
    -0.10
    TY
    -0.09
     Corona
    -0.09
    ounters
    -0.09
    ilde
    -0.09
    521
    -0.09
     wink
    -0.09
    ucht
    -0.09
     Welch
    -0.09
    POSITIVE LOGITS
     surprise
    0.29
     surprised
    0.27
     Surprise
    0.22
     surprises
    0.21
     unexpected
    0.19
     surpr
    0.17
     blinds
    0.15
     startled
    0.13
     surprising
    0.13
     unaware
    0.13
    Activations Density 0.016%

    No Known Activations