© 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. 111630
    Prev
    Next
    INDEX
    Explanations

    age and limitations

    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
     dre
    -0.09
     Laz
    -0.09
     Lazy
    -0.08
     Fork
    -0.08
    ean
    -0.08
    azine
    -0.07
     holy
    -0.07
    riger
    -0.07
     Pink
    -0.07
     #$
    -0.07
    POSITIVE LOGITS
     restrictions
    0.16
     verification
    0.16
     restriction
    0.15
     matters
    0.14
     notwithstanding
    0.14
     Verification
    0.13
    uve
    0.13
     Restrictions
    0.13
     Matters
    0.13
     verified
    0.12
    Activations Density 0.037%

    No Known Activations