© 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. 91396
    Prev
    Next
    INDEX
    Explanations

    politeness and decency

    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
     resistance
    -0.09
     Energ
    -0.08
     Resistance
    -0.08
     resistant
    -0.08
     Flexible
    -0.08
     unilateral
    -0.08
     resisting
    -0.08
     resisted
    -0.08
    Resistance
    -0.08
     Protected
    -0.07
    POSITIVE LOGITS
     manners
    0.44
     etiquette
    0.40
     polite
    0.37
     civ
    0.35
     civilized
    0.34
     courteous
    0.33
     courtesy
    0.31
     decency
    0.31
     rude
    0.29
     etiqu
    0.28
    Activations Density 0.108%

    No Known Activations