© 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. 31594
    Prev
    Next
    INDEX
    Explanations

    gay, lesbian, bisexual, transgender

    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
     teamwork
    -0.11
     interrogation
    -0.10
     tutoring
    -0.10
     torture
    -0.10
     Instant
    -0.10
     exec
    -0.09
     filtration
    -0.09
    WORDS
    -0.09
     crowds
    -0.09
     standardized
    -0.09
    POSITIVE LOGITS
     males
    0.20
     females
    0.18
     male
    0.18
     female
    0.17
    male
    0.14
     heterosexual
    0.14
     Female
    0.14
    female
    0.14
     Male
    0.13
    alsex
    0.13
    Activations Density 0.098%

    No Known Activations