© 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. 91721
    Prev
    Next
    INDEX
    Explanations

    LGBTQ+ and related identities

    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
     homosexuality
    -0.10
    abstract
    -0.10
     Lantern
    -0.10
     glowing
    -0.10
     Homemade
    -0.09
     Passenger
    -0.09
     homosexuals
    -0.09
     everlasting
    -0.09
     Cartoon
    -0.09
     Playoff
    -0.09
    POSITIVE LOGITS
     heterosexual
    0.38
     straight
    0.24
     heter
    0.22
    straight
    0.20
     Straight
    0.19
     mainstream
    0.18
     non
    0.16
    Straight
    0.16
     conservative
    0.14
     NON
    0.14
    Activations Density 0.406%

    No Known Activations