© 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. 29577
    Prev
    Next
    INDEX
    Explanations

    detective or inspector

    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
     terrorist
    -0.12
     military
    -0.11
     terrorists
    -0.10
     Military
    -0.10
     militar
    -0.10
     Nationals
    -0.09
     deployments
    -0.09
     prank
    -0.09
    Doctrine
    -0.09
     troops
    -0.09
    POSITIVE LOGITS
     detective
    0.29
     investigator
    0.26
     Detective
    0.24
     detectives
    0.23
     investigators
    0.22
     investigations
    0.21
     Investigations
    0.21
     noir
    0.21
     investigating
    0.20
     investigative
    0.20
    Activations Density 0.231%

    No Known Activations