© 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. 92404
    Prev
    Next
    INDEX
    Explanations

    moderate or mild intensity

    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
     unrelated
    -0.12
     ironically
    -0.11
     extreme
    -0.09
     ultra
    -0.09
     disproportionately
    -0.08
    ivy
    -0.08
    /null
    -0.08
    odb
    -0.08
    otype
    -0.08
    askan
    -0.08
    POSITIVE LOGITS
     moderately
    0.29
     moderate
    0.24
     slightly
    0.23
     Moderate
    0.23
     intermediate
    0.22
     medium
    0.22
     Intermediate
    0.21
     mildly
    0.21
     midd
    0.20
    Intermediate
    0.19
    Activations Density 0.659%

    No Known Activations