© 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. 6917
    Prev
    Next
    INDEX
    Explanations

    drug names and purchase information

    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
     stab
    -0.10
     outf
    -0.10
     Instruments
    -0.09
     facult
    -0.09
    еÐ
    -0.09
    worthy
    -0.09
     wen
    -0.09
    -fashioned
    -0.08
     dialect
    -0.08
     earm
    -0.08
    POSITIVE LOGITS
     price
    0.14
     official
    0.13
     dosage
    0.12
     Dos
    0.11
     effectiveness
    0.11
     refund
    0.11
     Price
    0.11
     vs
    0.11
     website
    0.10
     efficacy
    0.10
    Activations Density 0.022%

    No Known Activations