© 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. 13891
    Prev
    Next
    INDEX
    Explanations

    apologies or sorry followed by if

    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
     surv
    -0.11
     rejecting
    -0.09
    etas
    -0.09
     frightened
    -0.09
    yre
    -0.09
    rica
    -0.09
    FTER
    -0.09
     Haupt
    -0.09
    bro
    -0.09
     soc
    -0.08
    POSITIVE LOGITS
     upfront
    0.18
     beforehand
    0.17
     if
    0.14
     advance
    0.13
     ahead
    0.11
     apolog
    0.11
    advance
    0.11
     sincer
    0.11
     preempt
    0.10
     sincerely
    0.10
    Activations Density 0.024%

    No Known Activations