© 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. 17598
    Prev
    Next
    INDEX
    Explanations

    polite introductions

    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
     loving
    -0.15
     beloved
    -0.13
     cudd
    -0.13
     affection
    -0.13
     kisses
    -0.12
     Kiss
    -0.12
     hug
    -0.11
     kiss
    -0.11
     hugs
    -0.11
     kissing
    -0.11
    POSITIVE LOGITS
     politely
    0.23
     polite
    0.21
     stranger
    0.19
     strangers
    0.19
     introdu
    0.18
     polit
    0.16
     introduced
    0.15
     courte
    0.14
     introduction
    0.14
     manners
    0.14
    Activations Density 0.024%

    No Known Activations