© 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. 3485
    Prev
    Next
    INDEX
    Explanations

    web page services

    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
     curated
    -0.18
     hashtag
    -0.18
     Instagram
    -0.18
     hashtags
    -0.18
     emoji
    -0.17
     selfie
    -0.17
     apps
    -0.17
     Snapchat
    -0.17
     WhatsApp
    -0.16
     instagram
    -0.16
    POSITIVE LOGITS
     XHTML
    0.22
     Nets
    0.21
     Webcam
    0.19
     AOL
    0.19
     Yahoo
    0.19
     cgi
    0.18
     Web
    0.17
    activex
    0.17
    Yahoo
    0.17
     Acrobat
    0.16
    Activations Density 1.838%

    No Known Activations