© 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. 117417
    Prev
    Next
    INDEX
    Explanations

    struck head injury

    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
     Needle
    -0.13
     jig
    -0.12
     needles
    -0.11
    chas
    -0.11
     gown
    -0.11
     safely
    -0.10
     bree
    -0.10
     safe
    -0.10
     saf
    -0.10
     Lage
    -0.10
    POSITIVE LOGITS
     skull
    0.15
     skulls
    0.12
     clubs
    0.11
    swing
    0.11
     orbital
    0.11
     blunt
    0.11
     Skull
    0.11
     brick
    0.11
     head
    0.11
     beating
    0.11
    Activations Density 0.060%

    No Known Activations