© 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. 114295
    Prev
    Next
    INDEX
    Explanations

    racism or rac vs raco

    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
    eu
    -0.10
    -UA
    -0.09
    oble
    -0.09
    ardy
    -0.09
    enate
    -0.09
    former
    -0.09
    ingu
    -0.09
    voy
    -0.09
    yte
    -0.09
     Implemented
    -0.09
    POSITIVE LOGITS
     rac
    0.14
     Rac
    0.13
    aska
    0.10
     Richt
    0.10
    elif
    0.10
     racism
    0.09
    -striped
    0.09
    rac
    0.09
     tire
    0.09
    olta
    0.09
    Activations Density 0.018%

    No Known Activations