© 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. 31529
    Prev
    Next
    INDEX
    Explanations

    women

    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
     his
    -0.17
     prostate
    -0.16
     himself
    -0.15
     gay
    -0.15
     Actor
    -0.15
    his
    -0.15
     homosexual
    -0.14
    Boy
    -0.14
     boy
    -0.14
     Boy
    -0.14
    POSITIVE LOGITS
     women
    0.47
     Women
    0.41
    Women
    0.39
    women
    0.39
     womens
    0.37
     woman
    0.36
     ladies
    0.34
     girls
    0.33
     sisters
    0.32
     female
    0.32
    Activations Density 1.282%

    No Known Activations