© 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. 13856
    Prev
    Next
    INDEX
    Explanations

    phrases connecting to other words

    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
    thouse
    -0.09
     d
    -0.09
    sic
    -0.09
     Hil
    -0.09
    uml
    -0.09
    etre
    -0.09
     Lanc
    -0.09
    iem
    -0.09
     fluid
    -0.09
    attr
    -0.08
    POSITIVE LOGITS
     Clarence
    0.09
    bara
    0.09
    elo
    0.09
     everywhere
    0.09
    /py
    0.09
    pling
    0.08
     AAC
    0.08
    ìŀ¥
    0.08
     Betty
    0.08
    atron
    0.08
    Activations Density 0.001%

    No Known Activations