© 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. 92656
    Prev
    Next
    INDEX
    Explanations

    options or criteria for selection

    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
     blogging
    -0.11
    åľ¨çº¿
    -0.11
     mailing
    -0.11
     Rum
    -0.11
     Blogs
    -0.10
     substitutions
    -0.10
     Forums
    -0.10
     segue
    -0.10
     Blogger
    -0.10
     forum
    -0.10
    POSITIVE LOGITS
     deselect
    0.12
     indiscrim
    0.12
    cursor
    0.10
     swiper
    0.10
     manually
    0.10
     scrolled
    0.10
     swipe
    0.10
     Swipe
    0.10
     skipped
    0.10
     criteria
    0.09
    Activations Density 0.180%

    No Known Activations