© 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. 113733
    Prev
    Next
    INDEX
    Explanations

    smells like food

    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
    trash
    -0.11
     Jungle
    -0.10
     trash
    -0.09
     Shock
    -0.09
     Newport
    -0.09
     Zuk
    -0.09
    loe
    -0.09
     packing
    -0.09
     Compact
    -0.08
     misunderstood
    -0.08
    POSITIVE LOGITS
     smells
    0.29
     smelled
    0.27
     smelling
    0.26
     smell
    0.26
     arom
    0.23
     aroma
    0.22
     enticing
    0.20
     sniff
    0.19
     tantal
    0.19
     tempting
    0.18
    Activations Density 0.047%

    No Known Activations