© 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. 111618
    Prev
    Next
    INDEX
    Explanations

    all sides, times, four, or sizes

    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
    je
    -0.08
    orda
    -0.08
    ulan
    -0.08
    arent
    -0.08
    inct
    -0.08
    rey
    -0.08
    lov
    -0.08
    oust
    -0.07
     Banner
    -0.07
     sock
    -0.07
    POSITIVE LOGITS
     fours
    0.19
     quatre
    0.13
     stacked
    0.11
     four
    0.11
    {/
    0.11
    ･･
    0.10
     Niet
    0.10
    /posts
    0.10
    åĽĽ
    0.10
     Phillip
    0.10
    Activations Density 0.005%

    No Known Activations