© 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. 111570
    Prev
    Next
    INDEX
    Explanations

    "rom" variants

    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
    lian
    -0.11
    اء
    -0.10
    uncan
    -0.10
     Crane
    -0.10
    ria
    -0.10
     Canal
    -0.10
    str
    -0.10
    uin
    -0.09
    GF
    -0.09
    heavy
    -0.09
    POSITIVE LOGITS
    agnetic
    0.12
    ecast
    0.11
    ean
    0.11
    bose
    0.11
    etheus
    0.10
    ulent
    0.10
     Nimbus
    0.09
    bid
    0.09
    inance
    0.09
    etry
    0.09
    Activations Density 0.110%

    No Known Activations