© 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. 87826
    Prev
    Next
    INDEX
    Explanations

    longstanding utilization and belief

    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
     ecstasy
    -0.09
    Quest
    -0.09
     Sunderland
    -0.09
     discour
    -0.09
     еÑģÑĤÑĮ
    -0.09
     Brewer
    -0.08
    elastic
    -0.08
    bris
    -0.08
     franchises
    -0.08
    bid
    -0.08
    POSITIVE LOGITS
     heaps
    0.10
     tons
    0.10
    (sp
    0.10
     Kl
    0.10
     spi
    0.09
     pack
    0.09
     priorit
    0.09
     longstanding
    0.09
     sidel
    0.08
     tast
    0.08
    Activations Density 0.001%

    No Known Activations