© 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. 51024
    Prev
    Next
    INDEX
    Explanations

    automatic updates or checking

    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
     unconventional
    -0.09
     Starter
    -0.09
     baj
    -0.09
     misunder
    -0.08
    uko
    -0.08
     starters
    -0.08
    apult
    -0.08
     Transition
    -0.08
     lite
    -0.08
     misunderstood
    -0.08
    POSITIVE LOGITS
     updates
    0.62
     updating
    0.60
     update
    0.59
     updated
    0.57
     Updating
    0.53
     Updates
    0.52
    æĽ´æĸ°
    0.51
     Update
    0.49
    updates
    0.47
    Updating
    0.46
    Activations Density 1.016%

    No Known Activations