© 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. 7526
    Prev
    Next
    INDEX
    Explanations

    drug suffixes

    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
     Grü
    -0.11
     opi
    -0.11
    borg
    -0.11
     chemicals
    -0.11
     sincer
    -0.11
     Umb
    -0.11
     maté
    -0.10
    ipay
    -0.10
     accom
    -0.10
     stim
    -0.10
    POSITIVE LOGITS
     tablets
    0.15
     tablet
    0.14
     dosage
    0.13
     tabs
    0.12
     prescribed
    0.11
     generic
    0.11
    Inactive
    0.11
     tab
    0.11
     strengths
    0.11
     Tablets
    0.11
    Activations Density 0.978%

    No Known Activations