© 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. 50950
    Prev
    Next
    INDEX
    Explanations

    circumstances, rates, risks, extensions, routes, diseases, attitudes, language, method, proof

    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
    ,is
    -0.12
    mana
    -0.12
     Perf
    -0.11
    bidden
    -0.11
    ìĭł
    -0.11
    ENDED
    -0.11
    iar
    -0.11
     pcl
    -0.10
     refere
    -0.10
     Spiral
    -0.10
    POSITIVE LOGITS
     existed
    0.12
     exists
    0.12
     accompanies
    0.10
     they
    0.10
     exist
    0.10
     arises
    0.09
     preceded
    0.09
     awaits
    0.09
     we
    0.09
     awaited
    0.09
    Activations Density 0.058%

    No Known Activations