© 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. 8125
    Prev
    Next
    INDEX
    Explanations

    medical statistics and health prevention

    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
     Parr
    -0.10
     Moder
    -0.10
     moderately
    -0.09
     downright
    -0.09
    goog
    -0.09
     exter
    -0.09
    orang
    -0.09
    itical
    -0.09
    jac
    -0.09
    pee
    -0.09
    POSITIVE LOGITS
     bile
    0.12
     words
    0.11
     frustration
    0.10
     disappointment
    0.10
     bitterness
    0.10
     hysteria
    0.10
     losses
    0.10
    \"\
    0.10
     panic
    0.10
     foyer
    0.10
    Activations Density 0.004%

    No Known Activations