© 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. 87736
    Prev
    Next
    INDEX
    Explanations

    scientific abstracts

    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
     Bans
    -0.08
    Âł↵
    -0.08
     props
    -0.08
    arian
    -0.07
     Bad
    -0.07
     TRE
    -0.07
     Kash
    -0.07
    bane
    -0.07
    stab
    -0.07
    Âł
    -0.07
    POSITIVE LOGITS
    ADE
    0.11
     unfinished
    0.11
    ëĶ
    0.10
     wed
    0.10
    Invocation
    0.10
    juan
    0.10
     Janet
    0.10
    ALE
    0.10
     dung
    0.10
    ava
    0.10
    Activations Density 0.015%

    No Known Activations