© 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. 29400
    Prev
    Next
    INDEX
    Explanations

    jokes, laughing, humor

    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
     lonely
    -0.08
     distra
    -0.08
     fragile
    -0.08
     hesitant
    -0.08
     cps
    -0.07
     Stunning
    -0.07
     sweaty
    -0.07
     Wor
    -0.07
    dre
    -0.07
     submissive
    -0.07
    POSITIVE LOGITS
     joke
    0.68
     jokes
    0.67
     joking
    0.66
     laughing
    0.66
     humor
    0.65
     laugh
    0.65
     humorous
    0.64
     joked
    0.63
     laughter
    0.63
     laughs
    0.61
    Activations Density 0.742%

    No Known Activations