© 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. 3508
    Prev
    Next
    INDEX
    Explanations

    pursuing something relentlessly

    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
    aments
    -0.11
     pled
    -0.10
    emb
    -0.10
     pledge
    -0.10
     chewing
    -0.10
    amines
    -0.10
     Emb
    -0.10
    anza
    -0.10
    .modules
    -0.10
     listening
    -0.10
    POSITIVE LOGITS
     relentlessly
    0.11
     aggressively
    0.11
     elusive
    0.10
     vigorously
    0.10
     ache
    0.09
     gusto
    0.09
     dwind
    0.09
     pursue
    0.09
     skirts
    0.09
     validation
    0.08
    Activations Density 0.009%

    No Known Activations