© 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. 3472
    Prev
    Next
    INDEX
    Explanations

    professions and teaching

    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
     advisers
    -0.09
     proced
    -0.09
     backstage
    -0.08
     proceeding
    -0.08
     Proceed
    -0.08
     pruning
    -0.08
     proceed
    -0.08
     organisers
    -0.08
     fus
    -0.08
    /details
    -0.08
    POSITIVE LOGITS
     professionally
    0.21
    profession
    0.13
     commercially
    0.13
     weddings
    0.13
     profession
    0.13
     Profession
    0.13
     competit
    0.13
     specializing
    0.12
     freelance
    0.12
     gigs
    0.12
    Activations Density 0.212%

    No Known Activations