© 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. 27406
    Prev
    Next
    INDEX
    Explanations

    girl or girls

    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
     spouses
    -0.19
     spouse
    -0.18
     Wife
    -0.13
     womb
    -0.13
     wife
    -0.11
     Mrs
    -0.11
     prenatal
    -0.11
    Mrs
    -0.11
     Husband
    -0.11
    wife
    -0.11
    POSITIVE LOGITS
     girls
    0.55
     girl
    0.49
     Girls
    0.46
    Girls
    0.41
    girls
    0.41
     Girl
    0.39
    -girl
    0.38
     GIR
    0.34
    Girl
    0.34
    girl
    0.34
    Activations Density 0.179%

    No Known Activations