© 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. 25015
    Prev
    Next
    INDEX
    Explanations

    preparation, working, completion

    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
     countdown
    -0.09
     employ
    -0.09
    apan
    -0.09
     Blo
    -0.09
    iler
    -0.09
    EO
    -0.08
     declared
    -0.08
     Mist
    -0.08
     unle
    -0.08
     dep
    -0.08
    POSITIVE LOGITS
     drafting
    0.24
     prepare
    0.21
     draft
    0.20
     preparing
    0.20
     preparation
    0.20
     design
    0.20
     designing
    0.20
     preparations
    0.19
     Draft
    0.19
     drafts
    0.19
    Activations Density 0.755%

    No Known Activations