© 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. 46493
    Prev
    Next
    INDEX
    Explanations

    sudden realization or unexpected event

    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
     flaws
    -0.10
     Welch
    -0.10
    liner
    -0.10
    lut
    -0.09
    utan
    -0.09
     Hubb
    -0.09
     Wie
    -0.09
     vomiting
    -0.09
     tears
    -0.09
    bef
    -0.09
    POSITIVE LOGITS
     sight
    0.15
     sudden
    0.14
     sheer
    0.14
     unexpected
    0.13
     Sight
    0.13
     realization
    0.13
     unexpectedly
    0.12
     touch
    0.12
     proximity
    0.11
     realizing
    0.11
    Activations Density 0.024%

    No Known Activations