© 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. 18670
    Prev
    Next
    INDEX
    Explanations

    clauses starting with temporal or conditional words

    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
    ffen
    -0.11
    enstein
    -0.10
    uhn
    -0.09
    èle
    -0.09
    ...↵↵↵
    -0.09
    -it
    -0.09
    /utility
    -0.09
    agra
    -0.09
    ummer
    -0.09
     doen
    -0.09
    POSITIVE LOGITS
    /if
    0.14
     somewhere
    0.10
    /how
    0.09
    upon
    0.09
    åĥı
    0.08
     sometime
    0.08
    enge
    0.08
    oner
    0.08
     somew
    0.08
     aspects
    0.08
    Activations Density 0.754%

    No Known Activations