© 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. 47282
    Prev
    Next
    INDEX
    Explanations

    Coca-Cola and soda brands

    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
     grain
    -0.12
     Blanch
    -0.11
     Hemp
    -0.11
     Grain
    -0.10
     Stanford
    -0.10
     seeds
    -0.10
     sme
    -0.10
    TEE
    -0.09
     seed
    -0.09
     mast
    -0.09
    POSITIVE LOGITS
     soda
    0.33
     cola
    0.29
     Soda
    0.29
     Coke
    0.28
     sod
    0.27
     Pepsi
    0.27
     Coca
    0.27
     fiz
    0.26
     fizz
    0.25
     beverage
    0.24
    Activations Density 0.167%

    No Known Activations