© 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. 111492
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     lik
    -0.09
     goof
    -0.09
    unce
    -0.09
     IPL
    -0.09
    (...)↵
    -0.09
     Waters
    -0.09
    sto
    -0.08
    onna
    -0.08
    avy
    -0.08
    ÑģÑı
    -0.08
    POSITIVE LOGITS
     Produkt
    0.10
     obscure
    0.10
     mask
    0.09
    rio
    0.09
     cross
    0.09
     Johannes
    0.09
    /access
    0.09
    eko
    0.09
    phan
    0.09
    idis
    0.09
    Activations Density 0.000%

    No Known Activations