© 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. 3573
    Prev
    Next
    INDEX
    Explanations

    stress on words

    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
     frank
    -0.09
     Grip
    -0.09
     frags
    -0.09
     streak
    -0.09
    anko
    -0.08
    -self
    -0.08
     Eisen
    -0.08
    -fr
    -0.08
    Visibility
    -0.08
    tan
    -0.08
    POSITIVE LOGITS
     pronunciation
    0.36
     accent
    0.30
     pronounce
    0.28
     syll
    0.28
     pron
    0.27
     Pron
    0.27
     accents
    0.25
     pronounced
    0.25
     emphasis
    0.25
     vowels
    0.25
    Activations Density 0.120%

    No Known Activations