© 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. 111374
    Prev
    Next
    INDEX
    Explanations

    colors

    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
    lessly
    -0.13
    ful
    -0.11
     enough
    -0.11
    ullo
    -0.10
    -related
    -0.10
     Enough
    -0.10
    plusplus
    -0.10
     upside
    -0.10
    -minded
    -0.09
    less
    -0.09
    POSITIVE LOGITS
    /high
    0.12
     almost
    0.11
     verg
    0.11
     border
    0.10
     Almost
    0.09
    almost
    0.09
     (#
    0.08
     practically
    0.08
    ffiti
    0.08
    uration
    0.08
    Activations Density 0.005%

    No Known Activations