© 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. 111447
    Prev
    Next
    INDEX
    Explanations

    firearm actions and components

    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
     unarmed
    -0.17
     knives
    -0.15
     arrows
    -0.14
     Knife
    -0.12
     swords
    -0.12
    Knife
    -0.12
     knife
    -0.12
    knife
    -0.12
     needles
    -0.12
     armed
    -0.11
    POSITIVE LOGITS
     trigger
    0.16
     fir
    0.12
     cock
    0.12
    trigger
    0.12
     fired
    0.11
     firing
    0.11
     discharged
    0.11
     triggers
    0.11
     chamber
    0.11
     triggering
    0.11
    Activations Density 0.135%

    No Known Activations