© 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. 46311
    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
    Not in Any Lists

    No Comments

    Negative Logits
    allis
    -0.13
    ivor
    -0.12
     pathway
    -0.11
    IMS
    -0.10
     nrows
    -0.10
    cry
    -0.10
    alli
    -0.10
     Wilkinson
    -0.10
    ellers
    -0.10
     Lafayette
    -0.10
    POSITIVE LOGITS
     fier
    0.08
     ben
    0.08
     Gum
    0.08
     incre
    0.08
     bisc
    0.07
     bic
    0.07
    Localized
    0.07
     ment
    0.07
     Fang
    0.07
     legion
    0.07
    Activations Density 0.000%

    No Known Activations