© 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. 3722
    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
     Bat
    -0.10
    zia
    -0.09
    bay
    -0.09
     Cornwall
    -0.08
     Penn
    -0.08
    zi
    -0.08
     surrounds
    -0.08
     compromises
    -0.08
     compromise
    -0.08
     factory
    -0.08
    POSITIVE LOGITS
     neighbour
    0.10
     Jab
    0.10
     labour
    0.10
    sted
    0.10
     Moran
    0.09
    -desktop
    0.09
     Chim
    0.09
     tread
    0.09
    غ
    0.09
    ropp
    0.09
    Activations Density 0.000%

    No Known Activations