© 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. 92459
    Prev
    Next
    INDEX
    Explanations

    karma and forgiveness

    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
     escorted
    -0.10
     victory
    -0.10
    anner
    -0.10
     aut
    -0.10
     rallying
    -0.10
     frustration
    -0.10
    chez
    -0.10
     ruins
    -0.10
     placeholder
    -0.10
     Ru
    -0.10
    POSITIVE LOGITS
     karma
    0.31
     Karma
    0.31
     sins
    0.25
     accumulated
    0.17
     sin
    0.16
     reinc
    0.15
     repent
    0.15
     punishment
    0.15
     accumulate
    0.14
     redemption
    0.14
    Activations Density 0.043%

    No Known Activations