© 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. 34241
    Prev
    Next
    INDEX
    Explanations

    wellbore components and operations

    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
     walks
    -0.11
     marched
    -0.11
     walk
    -0.10
     stroll
    -0.10
     walking
    -0.10
    Walking
    -0.10
     walked
    -0.10
     wings
    -0.09
     rehe
    -0.09
     modeled
    -0.08
    POSITIVE LOGITS
     Hole
    0.11
    igit
    0.11
     protr
    0.11
    .intro
    0.10
     Grab
    0.10
     introdu
    0.10
     disemb
    0.10
     Pull
    0.10
     dangling
    0.10
     tantal
    0.10
    Activations Density 0.087%

    No Known Activations