© 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. 14114
    Prev
    Next
    INDEX
    Explanations

    body parts and possession

    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
     scl
    -0.10
     conj
    -0.10
     ceilings
    -0.10
     lids
    -0.09
     "?"
    -0.09
     Floors
    -0.08
     Holden
    -0.08
     lid
    -0.08
     fle
    -0.08
    cie
    -0.08
    POSITIVE LOGITS
     head
    0.16
     feet
    0.15
     torso
    0.14
     body
    0.14
     heads
    0.12
    身
    0.12
     face
    0.12
     bodies
    0.12
     hips
    0.12
     Head
    0.12
    Activations Density 0.019%

    No Known Activations