© 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. 46067
    Prev
    Next
    INDEX
    Explanations

    filter

    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
     barg
    -0.09
    pus
    -0.09
     registr
    -0.08
    hb
    -0.08
    hel
    -0.08
    aska
    -0.08
    toa
    -0.08
    lep
    -0.08
    $app
    -0.08
     wax
    -0.08
    POSITIVE LOGITS
     filter
    0.26
     filters
    0.26
     Filters
    0.23
    /filter
    0.23
     Filter
    0.22
     filtering
    0.22
    (filter
    0.22
    filters
    0.20
     Filtering
    0.20
    Filters
    0.19
    Activations Density 0.198%

    No Known Activations