© 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. 46249
    Prev
    Next
    INDEX
    Explanations

    his simulator

    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
    arker
    -0.09
    eus
    -0.09
     Inspiration
    -0.09
    eren
    -0.09
     Ree
    -0.08
    licit
    -0.08
     Bard
    -0.08
     twists
    -0.08
     Pri
    -0.08
    eti
    -0.08
    POSITIVE LOGITS
     ansch
    0.10
    fan
    0.10
     Verg
    0.09
    ogl
    0.09
     trademarks
    0.09
     decisive
    0.09
    ogo
    0.09
    aje
    0.09
     Bowen
    0.09
    OLT
    0.09
    Activations Density 0.001%

    No Known Activations