© 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. 34047
    Prev
    Next
    INDEX
    Explanations

    express gratitude or blame

    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
    pek
    -0.09
    observe
    -0.08
    agn
    -0.08
    afa
    -0.08
    olas
    -0.08
     Till
    -0.08
    iones
    -0.08
    UGH
    -0.08
    lyn
    -0.07
    998
    -0.07
    POSITIVE LOGITS
     them
    0.15
     him
    0.14
     anyone
    0.14
     anybody
    0.11
    them
    0.11
    elon
    0.11
     people
    0.11
     whoever
    0.10
     us
    0.10
    istory
    0.10
    Activations Density 0.002%

    No Known Activations