© 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. 92331
    Prev
    Next
    INDEX
    Explanations

    ray passive sensor system

    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
     prolific
    -0.09
     spree
    -0.08
     Vig
    -0.08
     complementary
    -0.08
     shortcut
    -0.08
    Shortcut
    -0.08
     crus
    -0.08
    ips
    -0.08
    831
    -0.08
     shortcuts
    -0.08
    POSITIVE LOGITS
     headlights
    0.25
     spotlight
    0.17
     predator
    0.16
     hunted
    0.15
     proverb
    0.14
     predators
    0.14
     flashlight
    0.14
     capture
    0.14
     trap
    0.14
     stare
    0.14
    Activations Density 0.004%

    No Known Activations