© 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. 48197
    Prev
    Next
    INDEX
    Explanations

    medicinal drugs and treatments

    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
     vÃŃ
    -0.12
    rats
    -0.12
     NRA
    -0.10
    hdr
    -0.10
     tou
    -0.10
     Oversight
    -0.10
     familia
    -0.10
    ìĥ
    -0.09
    aldo
    -0.09
     Moss
    -0.09
    POSITIVE LOGITS
     tablets
    0.13
     counterfeit
    0.12
     Tablets
    0.12
     sach
    0.11
     composition
    0.11
     genuine
    0.11
     expiry
    0.10
     jelly
    0.10
     compositions
    0.10
     capsules
    0.10
    Activations Density 0.102%

    No Known Activations