© 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. 50819
    Prev
    Next
    INDEX
    Explanations

    punishing past tense and participial endings

    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
    aat
    -0.10
    ihan
    -0.10
    strand
    -0.10
    eks
    -0.09
    oran
    -0.09
    thead
    -0.09
     Gul
    -0.09
    å¾Ħ
    -0.09
     Closing
    -0.09
     KIND
    -0.09
    POSITIVE LOGITS
    ners
    0.10
     punishing
    0.10
    ming
    0.09
     blister
    0.09
    /sl
    0.09
    /bl
    0.09
     cushion
    0.09
     lightly
    0.08
    /key
    0.08
    ing
    0.08
    Activations Density 0.009%

    No Known Activations