© 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. 3594
    Prev
    Next
    INDEX
    Explanations

    orders, proper, EXPECT, clean, Ig, what, sit, hands

    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
    olib
    -0.11
     torture
    -0.10
     coerc
    -0.10
    ibu
    -0.10
     ally
    -0.10
     nast
    -0.09
     somewhat
    -0.09
    endor
    -0.09
     imprison
    -0.08
     Pret
    -0.08
    POSITIVE LOGITS
     awaiting
    0.14
     greetings
    0.14
     silence
    0.13
     unless
    0.13
     awaits
    0.13
     silent
    0.13
     awaited
    0.12
     interrupted
    0.12
     humble
    0.12
     greet
    0.12
    Activations Density 0.031%

    No Known Activations