© 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. 14134
    Prev
    Next
    INDEX
    Explanations

    made in countries or locations

    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
     pardon
    -0.09
     Nah
    -0.08
     rut
    -0.08
    å¾ħ
    -0.08
    ione
    -0.08
     tow
    -0.08
     intermedi
    -0.08
     Roth
    -0.08
     ab
    -0.08
     prospect
    -0.08
    POSITIVE LOGITS
     laboratories
    0.17
     haste
    0.14
     workshops
    0.13
     labs
    0.13
     factories
    0.13
     cruc
    0.13
     laboratory
    0.12
     backstage
    0.12
     kitchens
    0.12
     Wol
    0.12
    Activations Density 0.599%

    No Known Activations