© 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. 24997
    Prev
    Next
    INDEX
    Explanations

    when followed by pronouns/names

    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
     dying
    -0.12
     Minutes
    -0.11
     Landing
    -0.10
     aba
    -0.09
     Carlton
    -0.09
    alla
    -0.09
    plat
    -0.09
     instr
    -0.09
     activation
    -0.09
     barg
    -0.09
    POSITIVE LOGITS
     baby
    0.08
    thic
    0.08
    -years
    0.08
     memberships
    0.08
    'e
    0.08
     Laur
    0.08
     Season
    0.08
    eli
    0.08
    onis
    0.08
     technology
    0.08
    Activations Density 0.195%

    No Known Activations