© 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. 87716
    Prev
    Next
    INDEX
    Explanations

    ancient civilization / cultures

    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
     disguised
    -0.12
     pard
    -0.11
     Wolves
    -0.10
    Exec
    -0.10
     wolves
    -0.10
     partisan
    -0.09
    wolf
    -0.09
     mut
    -0.09
    /exec
    -0.09
     Wolf
    -0.09
    POSITIVE LOGITS
     civilization
    0.36
     civilizations
    0.35
     Civilization
    0.29
     Bronze
    0.22
     civil
    0.20
     civilized
    0.20
     cultures
    0.19
     advanced
    0.19
     civ
    0.19
    civil
    0.19
    Activations Density 0.639%

    No Known Activations