© 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. 46575
    Prev
    Next
    INDEX
    Explanations

    herbal extracts and medicinal herbs

    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
     neon
    -0.11
     hygiene
    -0.11
     sog
    -0.11
     Neon
    -0.10
     fitted
    -0.10
    acro
    -0.09
     dough
    -0.09
     Hanson
    -0.09
     bathroom
    -0.09
     conting
    -0.09
    POSITIVE LOGITS
     herbal
    0.27
     herbs
    0.25
     Herbal
    0.22
     Gins
    0.21
     extracts
    0.21
     extract
    0.21
     Extract
    0.19
     herb
    0.18
    Extract
    0.18
     medicinal
    0.16
    Activations Density 0.552%

    No Known Activations