© 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. 3359
    Prev
    Next
    INDEX
    Explanations

    questions about what

    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
     Officials
    -0.11
     Gameplay
    -0.11
     Earlier
    -0.11
     Upon
    -0.11
    airo
    -0.11
     soon
    -0.10
     Quickly
    -0.10
    ollow
    -0.10
     unforgettable
    -0.10
    .Completed
    -0.10
    POSITIVE LOGITS
     Or
    0.12
     tl
    0.10
     Conversely
    0.10
    ometimes
    0.10
     How
    0.10
    Think
    0.10
    Or
    0.09
     If
    0.09
     if
    0.09
    >If
    0.09
    Activations Density 0.005%

    No Known Activations