© 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. 92410
    Prev
    Next
    INDEX
    Explanations

    people, groups, organizations

    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
    ichte
    -0.11
    —including
    -0.10
     prem
    -0.10
     ness
    -0.10
    —or
    -0.10
     itching
    -0.09
    ingly
    -0.09
    HING
    -0.09
     pods
    -0.09
     orbs
    -0.09
    POSITIVE LOGITS
     belonging
    0.15
     who
    0.15
     whom
    0.14
     residing
    0.12
     having
    0.11
     belonged
    0.10
     belong
    0.10
     dwelling
    0.10
    who
    0.10
     specialized
    0.10
    Activations Density 0.888%

    No Known Activations