© 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. 117515
    Prev
    Next
    INDEX
    Explanations

    saying "then"

    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
     distraction
    -0.09
     deny
    -0.09
     distract
    -0.09
     pant
    -0.08
     hysteria
    -0.08
     dif
    -0.08
    ignore
    -0.08
     Cal
    -0.08
     jag
    -0.08
    Cal
    -0.08
    POSITIVE LOGITS
     satisfied
    0.16
     then
    0.16
     nodded
    0.14
     satisfaction
    0.14
    THEN
    0.13
    then
    0.13
     proced
    0.13
     disappointed
    0.13
     THEN
    0.13
     Then
    0.13
    Activations Density 0.052%

    No Known Activations