© 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. 34053
    Prev
    Next
    INDEX
    Explanations

    features and product descriptions

    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
    -ish
    -0.10
     Ran
    -0.09
     loft
    -0.09
     ("-
    -0.09
     Nur
    -0.09
     też
    -0.09
     nue
    -0.09
    obra
    -0.09
    igest
    -0.08
     localized
    -0.08
    POSITIVE LOGITS
     boasts
    0.13
     proudly
    0.11
     fla
    0.10
     boasting
    0.10
     priorit
    0.09
     featuring
    0.09
     features
    0.09
     exclusively
    0.09
     sift
    0.09
     offers
    0.09
    Activations Density 0.238%

    No Known Activations