© 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. 46238
    Prev
    Next
    INDEX
    Explanations

    had followed by a word

    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
     gimm
    -0.09
     ambient
    -0.09
     randomness
    -0.08
     reward
    -0.08
     immedi
    -0.08
     infinit
    -0.08
     humming
    -0.08
     kiss
    -0.08
     wah
    -0.08
     IMM
    -0.08
    POSITIVE LOGITS
     previously
    0.12
     finally
    0.11
     hadn
    0.11
     never
    0.11
     already
    0.11
     recently
    0.10
    already
    0.10
     accum
    0.10
     hopes
    0.10
    rc
    0.10
    Activations Density 0.004%

    No Known Activations