© 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. 18561
    Prev
    Next
    INDEX
    Explanations

    police are investigating or hunting

    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
     fla
    -0.10
    ña
    -0.10
     instruct
    -0.10
     Reminder
    -0.10
    zu
    -0.10
    ajs
    -0.09
    /entity
    -0.09
     supplying
    -0.09
    anta
    -0.09
     Supply
    -0.09
    POSITIVE LOGITS
     arresting
    0.20
     arrest
    0.17
     arrests
    0.16
     investigating
    0.15
     appreh
    0.15
     hunt
    0.15
     traced
    0.15
     tracking
    0.14
     arrested
    0.14
     chasing
    0.13
    Activations Density 0.248%

    No Known Activations