© 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. 34217
    Prev
    Next
    INDEX
    Explanations

    body parts and biological entities

    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
     Sized
    -0.10
    allen
    -0.10
     chir
    -0.09
    /banner
    -0.09
     engineered
    -0.09
     minded
    -0.09
    ernet
    -0.09
     sized
    -0.09
     rigged
    -0.09
     flaming
    -0.09
    POSITIVE LOGITS
     confusing
    0.10
     Rescue
    0.09
     ceilings
    0.09
     proudly
    0.09
     excellence
    0.09
     Arbor
    0.09
     outfield
    0.09
     quadrant
    0.08
     Deliver
    0.08
     unpopular
    0.08
    Activations Density 0.091%

    No Known Activations