© 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. 5063
    Prev
    Next
    INDEX
    Explanations

    people, gendered terms

    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
     couples
    -0.25
     Couples
    -0.23
     couple
    -0.21
     Couple
    -0.20
     marriage
    -0.17
     Marriage
    -0.17
     romantic
    -0.16
     romant
    -0.15
     romance
    -0.15
    cou
    -0.15
    POSITIVE LOGITS
     women
    0.24
     men
    0.22
     girls
    0.20
    Women
    0.20
     ladies
    0.20
     Women
    0.20
    women
    0.20
    -men
    0.18
     boys
    0.18
     womens
    0.18
    Activations Density 0.159%

    No Known Activations