© 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. 32009
    Prev
    Next
    INDEX
    Explanations

    marriage and wealth

    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
     duct
    -0.12
    obl
    -0.11
    lv
    -0.11
     Maz
    -0.10
    uchi
    -0.10
     camar
    -0.10
     Slate
    -0.10
     challeng
    -0.10
     request
    -0.10
     Mast
    -0.10
    POSITIVE LOGITS
     marrying
    0.22
     marriage
    0.16
     wealthy
    0.16
     marry
    0.15
     inherit
    0.15
     inheritance
    0.15
     ambition
    0.14
     wealth
    0.14
     inherits
    0.14
     hei
    0.14
    Activations Density 0.031%

    No Known Activations