© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 13912
    Prev
    Next
    INDEX
    Explanations

    started, began, decided

    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
    Negative Logits
     twink
    -0.06
     Tw
    -0.05
    ()(
    -0.05
     typ
    -0.05
    Ī
    -0.05
     (>
    -0.05
     Parker
    -0.05
     Boots
    -0.05
     dign
    -0.04
    ä»ĸ
    -0.04
    POSITIVE LOGITS
     decided
    0.13
    's
    0.13
     had
    0.13
    isz
    0.13
    ’s
    0.13
     uses
    0.13
     began
    0.13
     did
    0.13
     felt
    0.13
     started
    0.13
    Activations Density 0.112%

    No Known Activations