© 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. 45966
    Prev
    Next
    INDEX
    Explanations

    enterprise, partnership, relationship, factor, map, heart, frontier, will

    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
     Glover
    -0.09
     bunker
    -0.09
    ibo
    -0.09
     seating
    -0.09
     selling
    -0.09
    universal
    -0.09
     crowd
    -0.09
     Actors
    -0.09
    Watching
    -0.08
     stern
    -0.08
    POSITIVE LOGITS
     mau
    0.10
     Aware
    0.10
     trunc
    0.09
    sson
    0.09
    ÑģÑĤва
    0.09
    ados
    0.09
     rainbow
    0.09
    ieu
    0.09
    ries
    0.09
     LEG
    0.08
    Activations Density 0.002%

    No Known Activations