© 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. 45975
    Prev
    Next
    INDEX
    Explanations

    prosecuting prosecutor

    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
     scouting
    -0.11
     testify
    -0.11
     reconnaissance
    -0.10
     spying
    -0.10
     finance
    -0.10
     broadcasting
    -0.10
    icode
    -0.10
     esc
    -0.09
     escape
    -0.09
     dj
    -0.09
    POSITIVE LOGITS
     prosecuting
    0.30
     prosec
    0.27
     prosecute
    0.27
     prosecutor
    0.26
     prosecutors
    0.26
     Prosec
    0.25
     Prosecutor
    0.23
    Prosec
    0.23
     prosecution
    0.21
     prosecutions
    0.21
    Activations Density 1.051%

    No Known Activations