© 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. 5236
    Prev
    Next
    INDEX
    Explanations

    temporal sequences after 'once' or 'after'

    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
    .lv
    -0.09
    .CR
    -0.09
    aldi
    -0.09
     Comet
    -0.09
     newcom
    -0.09
     rall
    -0.09
     Lew
    -0.09
    bak
    -0.08
    inel
    -0.08
    ÑĢам
    -0.08
    POSITIVE LOGITS
     once
    0.21
     Once
    0.17
    Once
    0.16
    once
    0.15
     afterward
    0.13
     AFTER
    0.13
     afterwards
    0.13
     after
    0.13
     watched
    0.12
     immediately
    0.11
    Activations Density 0.054%

    No Known Activations