© 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. 16856
    Prev
    Next
    INDEX
    Explanations

    male roles and masculinity

    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
     girl
    -0.20
     heroine
    -0.19
     herself
    -0.18
     Girl
    -0.18
     girls
    -0.17
     Girls
    -0.17
    Girls
    -0.15
     her
    -0.15
    Girl
    -0.15
     woman
    -0.15
    POSITIVE LOGITS
     prostate
    0.36
     masculinity
    0.23
     males
    0.18
     gentlemen
    0.18
     masculine
    0.18
     male
    0.17
     mascul
    0.17
     sons
    0.17
     Fathers
    0.17
     dads
    0.16
    Activations Density 0.028%

    No Known Activations