© 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. 87806
    Prev
    Next
    INDEX
    Explanations

    religious cults and movements

    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
     ang
    -0.09
     coal
    -0.09
     Dickens
    -0.09
     bravery
    -0.09
     restaur
    -0.09
     courage
    -0.09
     dames
    -0.08
     vict
    -0.08
     insol
    -0.08
     diplomats
    -0.08
    POSITIVE LOGITS
     cult
    0.42
     Cult
    0.28
     sect
    0.28
     followers
    0.26
     Followers
    0.25
    cult
    0.23
     Scientology
    0.23
     leader
    0.21
     follower
    0.21
    followers
    0.21
    Activations Density 0.282%

    No Known Activations