© 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. 51017
    Prev
    Next
    INDEX
    Explanations

    listing examples

    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
    fst
    -0.10
     respective
    -0.08
     NRF
    -0.08
    ese
    -0.08
    è±
    -0.07
     surviving
    -0.07
     edible
    -0.07
     Chili
    -0.07
    artin
    -0.07
     remaining
    -0.07
    POSITIVE LOGITS
     classics
    0.14
     favourites
    0.12
     traditional
    0.12
     favorites
    0.12
     standard
    0.11
     domest
    0.11
    743
    0.11
    Traditional
    0.11
     singles
    0.11
     brands
    0.11
    Activations Density 0.088%

    No Known Activations