© 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. 47445
    Prev
    Next
    INDEX
    Explanations

    pizza, delivery, end

    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
     Trader
    -0.08
    Trader
    -0.07
     cigars
    -0.07
     hose
    -0.07
     cocoa
    -0.07
     rel
    -0.07
    umes
    -0.07
     vendor
    -0.07
    bn
    -0.06
    cem
    -0.06
    POSITIVE LOGITS
    Pizza
    0.13
     Rao
    0.13
     Hut
    0.13
     Pizza
    0.13
     pizzas
    0.13
     Luigi
    0.12
     hut
    0.12
    dda
    0.12
     Kb
    0.12
     Pare
    0.12
    Activations Density 0.078%

    No Known Activations