© 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. 8053
    Prev
    Next
    INDEX
    Explanations

    . followed by descriptive text

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     honorable
    -0.10
    kc
    -0.10
    kee
    -0.09
     hardly
    -0.09
    ape
    -0.09
     buzzing
    -0.09
     Reco
    -0.08
     contro
    -0.08
    enga
    -0.08
    oppel
    -0.08
    POSITIVE LOGITS
     daylight
    0.09
     blitz
    0.09
    -flag
    0.09
     shr
    0.09
     circ
    0.09
    itz
    0.08
    -bed
    0.08
     Abel
    0.08
    DDS
    0.08
    agem
    0.08
    Activations Density 0.049%

    No Known Activations