© 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. 87681
    Prev
    Next
    INDEX
    Explanations

    Premier League or API

    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
     Beard
    -0.09
    Magn
    -0.07
     AG
    -0.07
     Cong
    -0.06
     end
    -0.06
    690
    -0.06
     exhaust
    -0.06
     bursting
    -0.06
     sever
    -0.06
     Brow
    -0.06
    POSITIVE LOGITS
    amel
    0.11
    antar
    0.10
    bras
    0.10
    itta
    0.10
     quir
    0.10
     Comet
    0.10
     referral
    0.10
     Assigned
    0.10
     BR
    0.10
    tra
    0.10
    Activations Density 0.001%

    No Known Activations