© 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. 50772
    Prev
    Next
    INDEX
    Explanations

    twinkle, tic-tac-toe, blah, boom

    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
     Kidd
    -0.10
     Gest
    -0.09
     immature
    -0.08
    ifa
    -0.08
    uppen
    -0.08
     ext
    -0.08
     Moore
    -0.08
     uphe
    -0.08
    upd
    -0.08
    ocide
    -0.08
    POSITIVE LOGITS
    ĥģ
    0.10
     relaxing
    0.10
    eline
    0.10
     IMS
    0.10
     crowned
    0.10
    enko
    0.09
     stag
    0.09
     Delta
    0.09
    loom
    0.09
    Iss
    0.09
    Activations Density 0.003%

    No Known Activations