© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32784
    Prev
    Next
    INDEX
    Explanations

    prejudice, discrimination, bias, racism, intolerance

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ach
    -0.10
     Wig
    -0.10
     dubious
    -0.09
     neglected
    -0.09
     ominous
    -0.09
     rop
    -0.09
     Roo
    -0.09
     carefully
    -0.08
    aru
    -0.08
     forfe
    -0.08
    POSITIVE LOGITS
     rampant
    0.15
     towards
    0.14
     discrimination
    0.13
     directed
    0.13
     toward
    0.12
     against
    0.12
    /op
    0.12
     Discrim
    0.12
    /pre
    0.11
     faced
    0.11
    Activations Density 0.139%

    No Known Activations