© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27661
    Prev
    Next
    INDEX
    Explanations

    tea and tea-related terms

    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
     Ferrari
    -0.11
     nightclub
    -0.11
     hog
    -0.11
     Carm
    -0.10
     Kurt
    -0.10
     slick
    -0.10
     discharge
    -0.10
     carnival
    -0.10
    BAR
    -0.10
     Disneyland
    -0.10
    POSITIVE LOGITS
     tea
    0.64
     Tea
    0.58
    tea
    0.46
     teas
    0.40
     brewed
    0.25
    Te
    0.24
     kettle
    0.23
     chai
    0.23
     TE
    0.22
    (te
    0.22
    Activations Density 0.218%

    No Known Activations