© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5471
    Prev
    Next
    INDEX
    Explanations

    surprise and satisfy

    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
     surprise
    -0.18
     surprises
    -0.17
     Surprise
    -0.14
     surprised
    -0.13
     surprising
    -0.12
    eree
    -0.11
     unsur
    -0.11
     surprisingly
    -0.11
     sights
    -0.10
    itas
    -0.09
    POSITIVE LOGITS
    zan
    0.11
     Lydia
    0.11
     expected
    0.10
     dov
    0.10
    147
    0.10
     delighted
    0.10
    pf
    0.09
     Pleasant
    0.09
    iu
    0.09
    Thought
    0.09
    Activations Density 0.111%

    No Known Activations