© 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. 33773
    Prev
    Next
    INDEX
    Explanations

    pause and sudden realization

    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
     verst
    -0.10
    ardo
    -0.10
     margins
    -0.09
    ate
    -0.09
    stroy
    -0.09
     Suff
    -0.09
    coni
    -0.09
     Weinstein
    -0.09
     earm
    -0.09
    auer
    -0.09
    POSITIVE LOGITS
     suddenly
    0.17
     noticing
    0.15
     pause
    0.15
     paused
    0.14
     Pause
    0.14
     pauses
    0.13
     Suddenly
    0.13
     sudden
    0.12
     realization
    0.12
    Suddenly
    0.12
    Activations Density 0.030%

    No Known Activations