© 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. 87982
    Prev
    Next
    INDEX
    Explanations

    waived, raid, rent, forming, trains, slipping, reset

    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
     Vie
    -0.10
    ác
    -0.09
     vie
    -0.09
     fro
    -0.09
    Hon
    -0.08
    undy
    -0.08
    ìł
    -0.08
    oin
    -0.08
    odi
    -0.08
    mic
    -0.08
    POSITIVE LOGITS
     conce
    0.09
     Pornhub
    0.09
    athe
    0.09
    éł
    0.09
     tinder
    0.09
    à¸Ķ
    0.09
    indx
    0.09
    lan
    0.08
     coc
    0.08
    /bl
    0.08
    Activations Density 0.017%

    No Known Activations