© 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. 117223
    Prev
    Next
    INDEX
    Explanations

    vertebral, creatinine, urinary, atypical, parenteral, quality

    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
    ätt
    -0.09
     unm
    -0.09
     Dent
    -0.09
     barley
    -0.09
    brook
    -0.08
     enough
    -0.08
     gray
    -0.08
     empty
    -0.08
     initial
    -0.08
     st
    -0.08
    POSITIVE LOGITS
     relaxing
    0.11
     massage
    0.10
     relaxation
    0.10
    AMED
    0.09
    ï¼ı
    0.09
    gba
    0.09
    /Dk
    0.09
     Relax
    0.09
     locally
    0.09
    [âĢ¦
    0.08
    Activations Density 0.001%

    No Known Activations