© 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. 90041
    Prev
    Next
    INDEX
    Explanations

    first women or female professionals

    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
     Kendall
    -0.13
     Marvin
    -0.11
     innocence
    -0.10
     generosity
    -0.10
     Khal
    -0.09
     Polynomial
    -0.09
     orally
    -0.09
    alte
    -0.09
     disconnected
    -0.09
    abis
    -0.09
    POSITIVE LOGITS
     gender
    0.29
     female
    0.29
     sexist
    0.26
     sexism
    0.26
     Gender
    0.25
     Female
    0.25
     females
    0.24
     women
    0.23
    Gender
    0.23
    female
    0.23
    Activations Density 0.415%

    No Known Activations