© 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. 46063
    Prev
    Next
    INDEX
    Explanations

    discrimination, injustice, prejudice, misconduct

    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
     softened
    -0.13
     repent
    -0.12
     confessed
    -0.12
     fug
    -0.11
     collaps
    -0.11
     blush
    -0.11
    irie
    -0.10
     lux
    -0.10
     loosen
    -0.10
     meltdown
    -0.10
    POSITIVE LOGITS
     unjust
    0.34
     unfairly
    0.33
     unfair
    0.31
     injustice
    0.30
     injust
    0.28
     discrimination
    0.24
     cruel
    0.23
     mist
    0.23
     persecution
    0.22
     Discrim
    0.22
    Activations Density 0.462%

    No Known Activations