© 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. 92668
    Prev
    Next
    INDEX
    Explanations

    want to ask a question

    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
    vil
    -0.12
    peg
    -0.10
     Gund
    -0.10
     Levy
    -0.10
    Sharper
    -0.10
     Ank
    -0.10
    igen
    -0.09
    pong
    -0.09
     Shan
    -0.09
    aat
    -0.09
    POSITIVE LOGITS
     Hacker
    0.08
    acre
    0.08
    ullo
    0.08
     stump
    0.08
    ugin
    0.08
     luz
    0.08
     Kre
    0.08
     Primer
    0.08
     Thi
    0.07
     Stripe
    0.07
    Activations Density 0.012%

    No Known Activations