© 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. 17410
    Prev
    Next
    INDEX
    Explanations

    marriage, union, licensed, wed

    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
     Workplace
    -0.09
     Busy
    -0.09
     Gomez
    -0.09
    din
    -0.09
    afb
    -0.09
    weit
    -0.09
    rena
    -0.09
     Workspace
    -0.09
    atta
    -0.09
     paw
    -0.09
    POSITIVE LOGITS
     consenting
    0.13
     anonymously
    0.11
     loving
    0.10
     mon
    0.10
    ErrorException
    0.10
     licensed
    0.10
     marriage
    0.10
     twink
    0.10
     sanctioned
    0.10
     wed
    0.10
    Activations Density 0.017%

    No Known Activations