© 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. 13875
    Prev
    Next
    INDEX
    Explanations

    being followed by -ing verbs

    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
     Searching
    -0.10
     Decorating
    -0.10
    Searching
    -0.10
    yles
    -0.09
     Selling
    -0.09
    aea
    -0.09
     Dancing
    -0.09
    ovo
    -0.09
    ominated
    -0.08
     Buying
    -0.08
    POSITIVE LOGITS
     being
    0.71
    being
    0.54
     Being
    0.45
    Being
    0.42
     becoming
    0.39
     having
    0.38
    è¢
    0.34
     sendo
    0.32
     needing
    0.31
    -being
    0.31
    Activations Density 0.681%

    No Known Activations