© 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. 45978
    Prev
    Next
    INDEX
    Explanations

    all-time records

    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
     newest
    -0.12
     Newest
    -0.11
    ater
    -0.10
     Schro
    -0.10
    endor
    -0.09
     Cath
    -0.09
     wieder
    -0.09
    idle
    -0.09
     Latest
    -0.09
    aters
    -0.09
    POSITIVE LOGITS
     ever
    0.26
    -ever
    0.24
     EVER
    0.21
    ever
    0.20
     greatest
    0.20
     Greatest
    0.18
     forever
    0.18
     all
    0.17
     timeless
    0.17
     Ever
    0.16
    Activations Density 0.280%

    No Known Activations