© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15023
    Prev
    Next
    INDEX
    Explanations

    spitting, CO2, ubiquitin, poop, poisoning, expiratory, BPA, creatinine

    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
    Not in Any Lists

    No Comments

    Negative Logits
     nud
    -0.12
     lace
    -0.10
    orsk
    -0.10
    adem
    -0.10
     blush
    -0.10
    unj
    -0.09
    .sul
    -0.09
    reds
    -0.09
     arou
    -0.09
     Lace
    -0.09
    POSITIVE LOGITS
    xit
    0.11
     Gron
    0.11
     Grim
    0.10
    ing
    0.09
    Cop
    0.09
     cop
    0.08
     McGr
    0.08
    ç«Ļ
    0.08
    -filled
    0.08
    etur
    0.08
    Activations Density 0.011%

    No Known Activations