© 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. 50758
    Prev
    Next
    INDEX
    Explanations

    all in one

    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
    ette
    -0.11
     thereof
    -0.10
    879
    -0.09
     Lori
    -0.09
    "*
    -0.08
    dna
    -0.08
    eo
    -0.08
    ettes
    -0.08
     Neo
    -0.08
     Aub
    -0.08
    POSITIVE LOGITS
     Bermuda
    0.09
    ingly
    0.09
     Timber
    0.09
    omba
    0.08
    usat
    0.08
    Bah
    0.08
    sd
    0.08
    gly
    0.08
     hollow
    0.08
    ustain
    0.08
    Activations Density 0.019%

    No Known Activations