© 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. 8041
    Prev
    Next
    INDEX
    Explanations

    names like Lei or Mei

    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
    krit
    -0.12
     rear
    -0.09
    apot
    -0.08
    anye
    -0.08
     Dumpster
    -0.08
     unnamed
    -0.08
    ams
    -0.08
    zug
    -0.08
    oxy
    -0.08
    odate
    -0.08
    POSITIVE LOGITS
    ÃŁe
    0.14
    ÃŁen
    0.13
    rink
    0.12
    hold
    0.10
    =UTF
    0.10
     MUT
    0.10
    wers
    0.10
    rie
    0.10
    ws
    0.10
    orado
    0.09
    Activations Density 0.069%

    No Known Activations