© 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. 13870
    Prev
    Next
    INDEX
    Explanations

    treated like royalty

    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
    inel
    -0.12
     fatally
    -0.11
     sanity
    -0.10
     thrott
    -0.10
     Zwe
    -0.09
     tort
    -0.09
    multip
    -0.09
     tainted
    -0.09
    Caption
    -0.09
    church
    -0.09
    POSITIVE LOGITS
     pam
    0.36
     luxury
    0.21
     luxurious
    0.20
     VIP
    0.20
     lux
    0.19
     lav
    0.19
     lavish
    0.19
     cared
    0.18
     treated
    0.18
     Pam
    0.17
    Activations Density 0.045%

    No Known Activations