© 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. 90861
    Prev
    Next
    INDEX
    Explanations

    gender roles and equality

    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
     thigh
    -0.11
    UDA
    -0.11
     misd
    -0.10
    abouts
    -0.10
    uda
    -0.10
    imary
    -0.10
    onical
    -0.10
    uve
    -0.10
     sac
    -0.10
    ally
    -0.10
    POSITIVE LOGITS
    ed
    0.12
     roles
    0.10
     critically
    0.10
     Tight
    0.10
    crit
    0.09
    obi
    0.09
    bere
    0.08
     sensible
    0.08
     Roles
    0.08
    PB
    0.08
    Activations Density 0.053%

    No Known Activations