© 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. 8208
    Prev
    Next
    INDEX
    Explanations

    user profiles and posts

    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
     naming
    -0.09
    ers
    -0.08
     fl
    -0.08
     dime
    -0.08
     earliest
    -0.08
    pot
    -0.08
    illac
    -0.07
    enberg
    -0.07
     commanders
    -0.07
     dau
    -0.07
    POSITIVE LOGITS
    Posts
    0.25
     Posts
    0.23
     Joined
    0.20
    Joined
    0.19
    -posts
    0.17
     posts
    0.17
    posts
    0.16
     joined
    0.15
    /posts
    0.14
    Points
    0.14
    Activations Density 0.145%

    No Known Activations