© 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. 33954
    Prev
    Next
    INDEX
    Explanations

    old, archaic, outdated concepts

    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
     NDEBUG
    -0.10
     attentive
    -0.10
     unarmed
    -0.10
    jen
    -0.09
    neutral
    -0.09
     unnamed
    -0.09
     remorse
    -0.09
     impost
    -0.09
     impe
    -0.09
     SOLD
    -0.09
    POSITIVE LOGITS
     outdated
    0.56
     antiqu
    0.45
     obsolete
    0.41
     old
    0.34
     dated
    0.32
     antique
    0.32
     primitive
    0.31
     relic
    0.29
     backward
    0.29
     ancient
    0.28
    Activations Density 0.642%

    No Known Activations