© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3352
    Prev
    Next
    INDEX
    Explanations

    dating and radioactive dating

    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
    Negative Logits
    brig
    -0.11
     Medium
    -0.09
     resh
    -0.09
     medium
    -0.09
     fitness
    -0.09
     reshape
    -0.09
     recruiter
    -0.08
     traf
    -0.08
     recruiters
    -0.08
     mim
    -0.08
    POSITIVE LOGITS
     dating
    0.27
     Dating
    0.25
     radioactive
    0.23
    Dating
    0.21
    dating
    0.21
     radi
    0.21
     dated
    0.19
     carbon
    0.19
     isot
    0.18
     Radi
    0.18
    Activations Density 0.166%

    No Known Activations