© 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. 117611
    Prev
    Next
    INDEX
    Explanations

    entering spaces

    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
    erton
    -0.10
    NH
    -0.09
    Desc
    -0.09
     Power
    -0.08
     bracket
    -0.08
     Shop
    -0.08
     SHOP
    -0.08
     Checkout
    -0.08
    -desc
    -0.08
    elen
    -0.08
    POSITIVE LOGITS
     condol
    0.11
     attic
    0.11
     demanding
    0.10
    sut
    0.10
    apon
    0.10
    horn
    0.09
    apan
    0.09
    -open
    0.09
     gast
    0.09
     nude
    0.09
    Activations Density 0.002%

    No Known Activations