© 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. 27064
    Prev
    Next
    INDEX
    Explanations

    slave, servant, subordinate

    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
     billionaires
    -0.11
     directors
    -0.10
     professors
    -0.10
     goddess
    -0.10
     owners
    -0.10
     proprietor
    -0.10
     propriet
    -0.10
     landlords
    -0.10
     bosses
    -0.10
     CEOs
    -0.10
    POSITIVE LOGITS
     slaves
    0.22
     slave
    0.21
     servant
    0.20
     minion
    0.19
     enslaved
    0.18
     servants
    0.18
     obedient
    0.17
     poor
    0.17
    slave
    0.17
     subordinate
    0.17
    Activations Density 0.087%

    No Known Activations