© 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. 87867
    Prev
    Next
    INDEX
    Explanations

    rolex watches, cameras, font metrics

    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
     Thornton
    -0.10
    "./
    -0.10
    adb
    -0.09
     irreversible
    -0.09
     qua
    -0.09
     plum
    -0.09
    dera
    -0.09
     Notebook
    -0.09
    fty
    -0.09
     zer
    -0.09
    POSITIVE LOGITS
     Levin
    0.09
     intercept
    0.09
    pp
    0.09
    izen
    0.09
     soft
    0.09
    iou
    0.09
    inp
    0.09
    JM
    0.08
     fle
    0.08
    akis
    0.08
    Activations Density 0.002%

    No Known Activations