© 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. 34081
    Prev
    Next
    INDEX
    Explanations

    Yin and Qin names

    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
     repl
    -0.09
    fried
    -0.08
    deb
    -0.07
     âĨ
    -0.07
     styl
    -0.07
     managed
    -0.07
    apot
    -0.07
    SCO
    -0.07
     inverse
    -0.07
    esses
    -0.07
    POSITIVE LOGITS
    åįİ
    0.11
    ering
    0.10
     gew
    0.10
    roi
    0.10
    anni
    0.10
     Ore
    0.10
     doen
    0.10
     lumber
    0.10
     luxury
    0.10
    rial
    0.10
    Activations Density 0.001%

    No Known Activations