© 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. 8111
    Prev
    Next
    INDEX
    Explanations

    lists and 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
     sab
    -0.08
     sco
    -0.08
     hometown
    -0.08
    aya
    -0.08
    386
    -0.08
     hass
    -0.08
    pu
    -0.08
    Č↵
    -0.08
     Bout
    -0.08
     Homepage
    -0.08
    POSITIVE LOGITS
    -wise
    0.10
    751
    0.09
    Than
    0.09
    efa
    0.09
     than
    0.09
     Nagar
    0.09
    enge
    0.09
     Ever
    0.09
    usat
    0.08
    622
    0.08
    Activations Density 0.217%

    No Known Activations