© 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. 117455
    Prev
    Next
    INDEX
    Explanations

    Proper nouns after conjunctions

    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
     Bey
    -0.10
     Netflix
    -0.10
     Tencent
    -0.10
     Peel
    -0.10
     LeBron
    -0.09
     «
    -0.09
     ime
    -0.09
     bey
    -0.09
    dat
    -0.09
     Benson
    -0.09
    POSITIVE LOGITS
     newcomer
    0.11
     alias
    0.11
     pseud
    0.10
    Narrated
    0.10
     debut
    0.10
     newbie
    0.09
     veteran
    0.09
     bogus
    0.09
     Dayton
    0.09
     toured
    0.09
    Activations Density 0.115%

    No Known Activations