© 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. 29231
    Prev
    Next
    INDEX
    Explanations

    obedience and submission

    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
     joking
    -0.13
     Laugh
    -0.13
     jokes
    -0.12
     dismissing
    -0.11
     laugh
    -0.11
     bene
    -0.11
     Cann
    -0.10
     laughs
    -0.10
     hilar
    -0.10
    Laugh
    -0.10
    POSITIVE LOGITS
     obedient
    0.36
     obedience
    0.35
     obey
    0.31
     obed
    0.28
     obe
    0.27
     submissive
    0.27
     disobed
    0.23
     disob
    0.23
     submission
    0.22
     respectfully
    0.21
    Activations Density 0.044%

    No Known Activations