© 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. 50943
    Prev
    Next
    INDEX
    Explanations

    @ property, if (m, airport FAQ

    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
    IDX
    -0.10
     Congressional
    -0.09
     resident
    -0.09
     Humph
    -0.09
    ani
    -0.09
    caf
    -0.09
     coh
    -0.09
    ba
    -0.09
     dorm
    -0.09
     domest
    -0.09
    POSITIVE LOGITS
     Meeting
    0.17
     mutually
    0.15
     mutual
    0.15
     meeting
    0.14
     Mutual
    0.14
    Meeting
    0.14
    meeting
    0.14
     Meet
    0.13
     introdu
    0.12
     initiator
    0.12
    Activations Density 0.001%

    No Known Activations