© 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. 7974
    Prev
    Next
    INDEX
    Explanations

    later or afterwards

    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
     fortunately
    -0.14
     surprisingly
    -0.14
     oh
    -0.13
    Fortunately
    -0.13
     Wouldn
    -0.13
     Fortunately
    -0.13
    fortunately
    -0.12
     luckily
    -0.12
     conveniently
    -0.11
     alas
    -0.11
    POSITIVE LOGITS
     later
    0.13
     Later
    0.13
    Later
    0.12
     Afterwards
    0.11
     lasts
    0.11
    later
    0.11
     afterwards
    0.10
     lasted
    0.10
     visible
    0.09
    [last
    0.09
    Activations Density 0.171%

    No Known Activations