© 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. 30776
    Prev
    Next
    INDEX
    Explanations

    beekeeping and honey production

    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
     Salah
    -0.08
     kidney
    -0.08
    .liferay
    -0.08
     gravy
    -0.08
     jul
    -0.08
     potato
    -0.08
    desk
    -0.08
     neph
    -0.08
     Felix
    -0.08
     Tommy
    -0.07
    POSITIVE LOGITS
     bee
    0.55
     bees
    0.54
     hive
    0.54
     honey
    0.52
     Hive
    0.46
     Bee
    0.46
     Honey
    0.45
    hive
    0.43
    bee
    0.40
     sting
    0.39
    Activations Density 0.786%

    No Known Activations