© 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. 34154
    Prev
    Next
    INDEX
    Explanations

    month day, year

    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
     spear
    -0.11
    tout
    -0.09
    claimer
    -0.09
     Sche
    -0.09
     targ
    -0.09
    tero
    -0.09
    hift
    -0.09
     tern
    -0.09
     Als
    -0.09
    hib
    -0.09
    POSITIVE LOGITS
     bas
    0.09
    omain
    0.08
     distressed
    0.08
    inkle
    0.08
    Bas
    0.08
    _ERR
    0.08
    068
    0.08
    أ
    0.08
     Hastings
    0.08
    bas
    0.08
    Activations Density 0.073%

    No Known Activations