© 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. 14009
    Prev
    Next
    INDEX
    Explanations

    treasure trove, toolbox, source, pot

    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
     Nichols
    -0.10
    arkin
    -0.10
    uran
    -0.10
     Bip
    -0.10
     Spl
    -0.10
     downs
    -0.09
    ansa
    -0.09
     neglig
    -0.09
    upal
    -0.09
     surely
    -0.09
    POSITIVE LOGITS
    avar
    0.09
     tapered
    0.09
    ker
    0.09
    isch
    0.09
     Nature
    0.08
    raz
    0.08
    Lint
    0.08
    four
    0.08
    chg
    0.07
     Briggs
    0.07
    Activations Density 0.003%

    No Known Activations