© 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. 50956
    Prev
    Next
    INDEX
    Explanations

    fulfillment, time, and service

    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
    ago
    -0.10
     _______,
    -0.09
    abar
    -0.09
     Beit
    -0.07
     Kw
    -0.07
     Kathryn
    -0.07
    KW
    -0.07
     Craig
    -0.07
    apus
    -0.07
    Destroyed
    -0.07
    POSITIVE LOGITS
     Garn
    0.10
    ient
    0.09
     servi
    0.09
    .neo
    0.09
     gossip
    0.09
    Johnny
    0.09
     Banner
    0.09
     ull
    0.09
     Conserv
    0.09
     Johnny
    0.08
    Activations Density 0.863%

    No Known Activations