© 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. 111431
    Prev
    Next
    INDEX
    Explanations

    incest and inbreeding

    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
     nightlife
    -0.10
     ladies
    -0.08
     posture
    -0.08
     Tiffany
    -0.08
    erts
    -0.08
     Bai
    -0.08
     toughness
    -0.07
     jets
    -0.07
     Palest
    -0.07
     Automation
    -0.07
    POSITIVE LOGITS
     incest
    0.56
     sibling
    0.36
     siblings
    0.32
    cest
    0.32
    ince
    0.31
     familial
    0.31
     brother
    0.29
    Sibling
    0.28
     cousin
    0.27
     relatives
    0.26
    Activations Density 0.132%

    No Known Activations