© 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. 25163
    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
     Gros
    -0.11
     nast
    -0.11
     slur
    -0.10
     Cop
    -0.10
    oce
    -0.10
     weighting
    -0.09
    uhl
    -0.09
    anh
    -0.09
    ÑıÑĤÑĮ
    -0.09
     cop
    -0.09
    POSITIVE LOGITS
    ạn
    0.10
    cu
    0.09
    ein
    0.09
    .cf
    0.09
    eding
    0.09
    iew
    0.09
    kov
    0.09
    imd
    0.09
     dere
    0.09
     ther
    0.08
    Activations Density 0.000%

    No Known Activations