© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5527
    Prev
    Next
    INDEX
    Explanations

    low back pain and spinal injuries

    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
    Not in Any Lists

    No Comments

    Negative Logits
     jitter
    -0.11
     Brill
    -0.10
     bleed
    -0.10
     bleeding
    -0.09
    uem
    -0.09
     orally
    -0.08
     Linden
    -0.08
     Greenwood
    -0.08
     decision
    -0.08
     Norman
    -0.08
    POSITIVE LOGITS
     spine
    0.24
     chiropr
    0.23
     neck
    0.23
     ergonomic
    0.22
     spinal
    0.22
     strain
    0.22
     Neck
    0.22
     hern
    0.21
     posture
    0.21
     injuries
    0.21
    Activations Density 0.454%

    No Known Activations