© 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. 116091
    Prev
    Next
    INDEX
    Explanations

    radioactive material and radiation

    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
     Julien
    -0.11
    .AD
    -0.09
     Synthetic
    -0.09
     CSL
    -0.09
     fatty
    -0.09
     Gly
    -0.09
    ASA
    -0.09
     verv
    -0.09
     Grinder
    -0.09
    gly
    -0.09
    POSITIVE LOGITS
     radioactive
    0.56
     nuclear
    0.54
     radiation
    0.52
     Nuclear
    0.51
     Radiation
    0.49
     uranium
    0.44
     irradi
    0.41
     atomic
    0.38
     Atomic
    0.38
    Radi
    0.35
    Activations Density 1.784%

    No Known Activations