© 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. 87901
    Prev
    Next
    INDEX
    Explanations

    tournament rounds and eliminations

    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
     starving
    -0.11
     dow
    -0.09
     Cave
    -0.09
    Plans
    -0.09
    á»ķi
    -0.09
     misc
    -0.08
    redits
    -0.08
     swung
    -0.08
    /manual
    -0.08
     Snyder
    -0.08
    POSITIVE LOGITS
     elimination
    0.37
     elim
    0.37
     eliminated
    0.34
     Elim
    0.33
     elimin
    0.33
     semif
    0.32
    Elim
    0.30
     eliminate
    0.28
    elim
    0.28
     eliminates
    0.28
    Activations Density 0.667%

    No Known Activations