© 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. 34061
    Prev
    Next
    INDEX
    Explanations

    option to, tendency of, flexibility of, requirement to, concern with, idea of, ideas for, facility to, intention of

    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
    ulin
    -0.11
    tractor
    -0.11
     Palmer
    -0.10
    CHO
    -0.10
     trending
    -0.10
     Tray
    -0.10
     wholesale
    -0.10
    HOUSE
    -0.10
     pers
    -0.10
     Wer
    -0.10
    POSITIVE LOGITS
     towards
    0.10
     Towards
    0.09
     og
    0.08
    oad
    0.08
     inc
    0.07
     concerning
    0.07
    Towards
    0.07
     how
    0.07
     to
    0.07
    ope
    0.07
    Activations Density 1.147%

    No Known Activations