© 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. 8174
    Prev
    Next
    INDEX
    Explanations

    numbers followed by operators or variables

    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
     crunch
    -0.09
     Mund
    -0.08
    NSS
    -0.08
    IFF
    -0.08
    /item
    -0.08
    mens
    -0.08
    Ca
    -0.08
    ernet
    -0.08
    ende
    -0.07
     IDD
    -0.07
    POSITIVE LOGITS
     Perry
    0.12
     ons
    0.11
     medically
    0.11
    (#)
    0.11
     Frost
    0.10
    ;break
    0.10
     ì´Ī
    0.10
     supplementary
    0.10
     Roose
    0.09
     Santos
    0.09
    Activations Density 0.181%

    No Known Activations