© 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. 18696
    Prev
    Next
    INDEX
    Explanations

    unordered list (`<ul>`)

    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
    ATOR
    -0.13
    ate
    -0.12
    QL
    -0.10
     alternating
    -0.10
    ará
    -0.10
    te
    -0.09
    uhan
    -0.09
    ator
    -0.09
    in
    -0.09
    unately
    -0.09
    POSITIVE LOGITS
    thood
    0.12
    ski
    0.11
     Pods
    0.11
     fore
    0.11
    enko
    0.10
    ièrement
    0.10
    monary
    0.10
    enk
    0.10
    sel
    0.10
    sd
    0.10
    Activations Density 0.101%

    No Known Activations