© 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. 16218
    Prev
    Next
    INDEX
    Explanations

    male and female comparisons

    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
    /local
    -0.10
    noch
    -0.10
    omic
    -0.10
    azzi
    -0.09
     Wick
    -0.09
     acad
    -0.09
    zik
    -0.09
    hoff
    -0.09
     citiz
    -0.09
     laminate
    -0.09
    POSITIVE LOGITS
     male
    0.52
     female
    0.47
     males
    0.43
     Male
    0.41
    male
    0.39
     masculine
    0.39
     females
    0.39
     Female
    0.38
    Male
    0.37
    çĶ·
    0.36
    Activations Density 0.778%

    No Known Activations