© 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. 46139
    Prev
    Next
    INDEX
    Explanations

    began his career/activity

    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
     Rolls
    -0.09
    antis
    -0.08
    izoph
    -0.08
    &t
    -0.08
     prof
    -0.08
    ace
    -0.08
    iks
    -0.08
    adia
    -0.07
     Hep
    -0.07
    eya
    -0.07
    POSITIVE LOGITS
     professionally
    0.14
     humble
    0.12
     modest
    0.12
     blogging
    0.11
     formally
    0.11
     seriously
    0.10
    bone
    0.10
    eniable
    0.10
    ACY
    0.10
    tron
    0.10
    Activations Density 0.244%

    No Known Activations