© 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. 13881
    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
    enet
    -0.12
    alo
    -0.11
     Celt
    -0.10
    Bear
    -0.10
    eko
    -0.09
     Passage
    -0.09
    /th
    -0.09
    IMA
    -0.09
    703
    -0.09
    ullet
    -0.09
    POSITIVE LOGITS
     pam
    0.09
     Ruf
    0.09
    awan
    0.09
     qualifier
    0.08
    /context
    0.08
    abwe
    0.08
     Pins
    0.08
     wil
    0.08
    .CONT
    0.08
    xing
    0.08
    Activations Density 0.000%

    No Known Activations