© 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. 50844
    Prev
    Next
    INDEX
    Explanations

    documentation files

    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
    !↵↵↵↵↵↵
    -0.10
    --↵
    -0.10
     :↵↵↵↵
    -0.10
     Bun
    -0.09
    erve
    -0.09
    amu
    -0.09
    emain
    -0.09
     daytime
    -0.09
     chim
    -0.09
     aftermath
    -0.09
    POSITIVE LOGITS
     distract
    0.11
     prepar
    0.09
    nes
    0.09
    PIO
    0.09
     startling
    0.09
    ged
    0.09
    rost
    0.08
     Hart
    0.08
     distracted
    0.08
     pret
    0.08
    Activations Density 0.004%

    No Known Activations