© 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. 6014
    Prev
    Next
    INDEX
    Explanations

    gay 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
    åĵģ
    -0.09
     Hog
    -0.09
    ivy
    -0.09
    iegel
    -0.09
     electr
    -0.08
    charm
    -0.08
     sac
    -0.08
     Ud
    -0.08
    imi
    -0.08
    utz
    -0.08
    POSITIVE LOGITS
    /trans
    0.18
    ety
    0.16
    atri
    0.15
    -friendly
    0.14
    dar
    0.14
    lord
    0.12
     tendencies
    0.12
    lords
    0.12
    -themed
    0.12
     cruising
    0.11
    Activations Density 0.115%

    No Known Activations