© 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. 45974
    Prev
    Next
    INDEX
    Explanations

    stay tuned

    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
    ines
    -0.09
    aret
    -0.09
    oman
    -0.08
    aga
    -0.08
     Schro
    -0.08
    olini
    -0.07
    ino
    -0.07
     pleasing
    -0.07
    angu
    -0.07
     %{
    -0.07
    POSITIVE LOGITS
     Stay
    0.72
     stay
    0.72
    Stay
    0.64
    stay
    0.60
     stayed
    0.55
     stays
    0.54
     staying
    0.41
     Tune
    0.35
     tune
    0.32
     tuned
    0.31
    Activations Density 0.224%

    No Known Activations