© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 45962
    Prev
    Next
    INDEX
    Explanations

    politeness and reputation

    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
    Negative Logits
     spont
    -0.11
     excitement
    -0.11
     Lover
    -0.11
     chore
    -0.11
     fearless
    -0.10
     Couples
    -0.10
    -risk
    -0.10
    sessions
    -0.10
    ipes
    -0.10
     danger
    -0.10
    POSITIVE LOGITS
     karma
    0.22
     Karma
    0.21
     recipro
    0.16
     recip
    0.16
     kindness
    0.16
     goodwill
    0.15
     reputation
    0.15
     Courtesy
    0.14
     reciprocal
    0.13
     courtesy
    0.13
    Activations Density 0.094%

    No Known Activations