© 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. 90398
    Prev
    Next
    INDEX
    Explanations

    food, meals, dining, cuisine, dinner, gastronomy

    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
    rax
    -0.09
     compression
    -0.08
     multip
    -0.08
     freak
    -0.08
    yny
    -0.08
     compress
    -0.08
    apur
    -0.08
     Figure
    -0.08
     multiplication
    -0.07
    esz
    -0.07
    POSITIVE LOGITS
     cooked
    0.14
    (food
    0.12
    /dr
    0.12
     hearty
    0.12
     served
    0.12
     eaten
    0.12
     dinner
    0.12
    cooked
    0.12
    akis
    0.12
    -secondary
    0.11
    Activations Density 0.051%

    No Known Activations