© 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. 34069
    Prev
    Next
    INDEX
    Explanations

    doing/in

    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
    anos
    -0.11
    anie
    -0.09
     Anat
    -0.09
     Wer
    -0.09
     Alb
    -0.09
    opo
    -0.09
     Lansing
    -0.09
    alu
    -0.09
    anth
    -0.08
     Mash
    -0.08
    POSITIVE LOGITS
     doing
    0.40
     Doing
    0.35
    doing
    0.34
    Doing
    0.34
     do
    0.19
    åģ
    0.19
    	do
    0.17
     dabei
    0.16
    do
    0.16
    .do
    0.16
    Activations Density 0.226%

    No Known Activations