© 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. 50583
    Prev
    Next
    INDEX
    Explanations

    LGBTQ+ and transgender topics

    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
     homosexual
    -0.21
     male
    -0.18
     homosexuality
    -0.17
     homosexuals
    -0.17
     homosex
    -0.17
     males
    -0.17
     gay
    -0.16
     female
    -0.15
     masculinity
    -0.13
     masculine
    -0.13
    POSITIVE LOGITS
    /trans
    0.12
     Trans
    0.12
     Pron
    0.11
     transf
    0.10
     Ston
    0.10
     Cait
    0.10
     Visibility
    0.10
     trans
    0.10
     ignorant
    0.10
     harassment
    0.10
    Activations Density 0.218%

    No Known Activations