© 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. 29460
    Prev
    Next
    INDEX
    Explanations

    receive updates and notifications

    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
    DT
    -0.11
     Bust
    -0.11
    <?,
    -0.10
     bust
    -0.10
     Ire
    -0.10
    ERE
    -0.10
    itia
    -0.10
    .mx
    -0.09
    ats
    -0.09
     bounty
    -0.09
    POSITIVE LOGITS
     notifications
    0.15
     alerts
    0.12
     updates
    0.12
     emails
    0.10
     announcements
    0.10
     invitations
    0.10
    _notifications
    0.10
     exclusive
    0.10
    Notifications
    0.10
    notifications
    0.10
    Activations Density 0.038%

    No Known Activations