© 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. 18709
    Prev
    Next
    INDEX
    Explanations

    verbs ending in ing

    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
     somehow
    -0.09
     disemb
    -0.09
     Wallace
    -0.09
    –and
    -0.09
    adan
    -0.09
    RAP
    -0.08
    Kenn
    -0.08
    ums
    -0.08
     surely
    -0.08
     basically
    -0.08
    POSITIVE LOGITS
     sophomore
    0.12
     alone
    0.09
     continuously
    0.09
     dane
    0.09
     aisle
    0.09
     procession
    0.09
     heiÃŁ
    0.09
     cuales
    0.09
    ETCH
    0.09
     continually
    0.09
    Activations Density 0.279%

    No Known Activations