© 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. 117358
    Prev
    Next
    INDEX
    Explanations

    key figure or role

    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
     father
    -0.12
     parents
    -0.10
    father
    -0.09
     parent
    -0.09
     mother
    -0.09
     populated
    -0.09
     Rol
    -0.08
    638
    -0.08
     dominant
    -0.08
     owners
    -0.08
    POSITIVE LOGITS
     prized
    0.16
     newest
    0.15
     guest
    0.15
     emiss
    0.14
     priceless
    0.14
     centerpiece
    0.13
    guest
    0.13
     bait
    0.13
     Guest
    0.13
     VIP
    0.13
    Activations Density 0.201%

    No Known Activations