© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115017
    Prev
    Next
    INDEX
    Explanations

    race and color

    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
     Exxon
    -0.09
     Preston
    -0.09
     atmos
    -0.08
     stitches
    -0.08
    sla
    -0.08
     swinger
    -0.08
     Adults
    -0.08
    agraph
    -0.08
     sluts
    -0.08
     french
    -0.08
    POSITIVE LOGITS
     racial
    0.34
     racially
    0.32
     skin
    0.32
     race
    0.31
     ethnicity
    0.29
     races
    0.29
     white
    0.28
    Race
    0.28
    racial
    0.28
     Race
    0.28
    Activations Density 0.169%

    No Known Activations