© 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. 17150
    Prev
    Next
    INDEX
    Explanations

    sandwich or sandwiches

    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
     bucket
    -0.12
     cooking
    -0.12
     dinners
    -0.11
     dessert
    -0.11
     Alibaba
    -0.11
     Bucket
    -0.10
     buckets
    -0.10
     scal
    -0.10
     dinner
    -0.10
    bucket
    -0.10
    POSITIVE LOGITS
     sandwich
    0.38
     Sandwich
    0.37
     sandwiches
    0.37
     bread
    0.26
     Subway
    0.24
     Bread
    0.21
     SAND
    0.19
    bread
    0.19
     toast
    0.18
    sand
    0.17
    Activations Density 0.179%

    No Known Activations