© 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. 3420
    Prev
    Next
    INDEX
    Explanations

    sin and temptation

    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
     altru
    -0.13
     martyr
    -0.12
     humane
    -0.12
    ppo
    -0.11
     relig
    -0.11
     religious
    -0.11
     Religious
    -0.11
     Ethics
    -0.11
     ethic
    -0.11
     Marty
    -0.11
    POSITIVE LOGITS
     sin
    0.25
     Sin
    0.20
     SIN
    0.19
     sins
    0.19
    Sin
    0.18
    sin
    0.16
    _sin
    0.15
     sinful
    0.14
    .sin
    0.14
     committing
    0.13
    Activations Density 0.134%

    No Known Activations