© 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. 46186
    Prev
    Next
    INDEX
    Explanations

    ages, temperatures, and counts

    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
     muted
    -0.08
    QUEST
    -0.08
     Ez
    -0.08
     approving
    -0.07
    åij
    -0.07
    alla
    -0.07
     secular
    -0.07
     sust
    -0.06
     quar
    -0.06
     aut
    -0.06
    POSITIVE LOGITS
     Prop
    0.13
     Twice
    0.12
     impres
    0.12
    -prop
    0.11
     stumbled
    0.11
     cand
    0.11
     stumble
    0.11
    inan
    0.11
    Editors
    0.10
    -stars
    0.10
    Activations Density 0.002%

    No Known Activations