© 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. 7793
    Prev
    Next
    INDEX
    Explanations

    differences between groups, races, or countries

    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
     asymmetric
    -0.09
    umba
    -0.09
     actions
    -0.08
    ASA
    -0.08
     imperfect
    -0.08
    atr
    -0.08
     consolid
    -0.08
     simplified
    -0.08
    Sock
    -0.07
     Prod
    -0.07
    POSITIVE LOGITS
     averages
    0.17
     average
    0.17
     races
    0.14
     Africans
    0.14
     systematically
    0.14
     averaging
    0.13
    verages
    0.13
    Average
    0.13
     populations
    0.13
    -average
    0.13
    Activations Density 0.394%

    No Known Activations