© 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. 46281
    Prev
    Next
    INDEX
    Explanations

    blood clots and veins

    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
     Clothes
    -0.14
     clothing
    -0.13
     clothes
    -0.11
     clad
    -0.11
     Clothing
    -0.11
     Closed
    -0.11
     Plates
    -0.10
     uphol
    -0.10
     Trevor
    -0.10
     jeans
    -0.10
    POSITIVE LOGITS
     cr
    0.11
     NAS
    0.11
     Wall
    0.11
     partner
    0.10
     rolled
    0.10
     wrinkles
    0.10
     partnered
    0.10
     tubes
    0.09
     toes
    0.09
     Beaut
    0.09
    Activations Density 0.078%

    No Known Activations