© 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. 46092
    Prev
    Next
    INDEX
    Explanations

    saying goodbye or good riddance

    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
     ditch
    -0.14
     detriment
    -0.13
     goodbye
    -0.13
     Fare
    -0.12
     unst
    -0.11
    iaux
    -0.11
    ullo
    -0.11
     Bris
    -0.10
    ami
    -0.10
     supplement
    -0.10
    POSITIVE LOGITS
     Turnbull
    0.10
     fundament
    0.09
     cork
    0.09
     Cop
    0.08
     cop
    0.08
    /_
    0.08
    Et
    0.08
     specially
    0.08
    vt
    0.07
    -hours
    0.07
    Activations Density 0.001%

    No Known Activations