© 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. 111398
    Prev
    Next
    INDEX
    Explanations

    aqu words

    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
    ometry
    -0.10
     literal
    -0.08
     rus
    -0.08
    oub
    -0.08
     Greek
    -0.08
    rouch
    -0.08
    ivism
    -0.07
     motivational
    -0.07
     reinforced
    -0.07
    kim
    -0.07
    POSITIVE LOGITS
     acqu
    0.13
     apolog
    0.11
     acquitted
    0.11
    anno
    0.11
    ilar
    0.11
    /ac
    0.10
    asan
    0.10
    ecer
    0.10
    Slf
    0.10
    inis
    0.10
    Activations Density 0.018%

    No Known Activations