© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32158
    Prev
    Next
    INDEX
    Explanations

    thrombosis and related medical terms

    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
    iap
    -0.09
    iative
    -0.08
     Bell
    -0.08
    oter
    -0.08
    iya
    -0.08
    prompt
    -0.08
    mom
    -0.08
    limit
    -0.08
    lish
    -0.08
    rai
    -0.08
    POSITIVE LOGITS
     thro
    0.15
    bbing
    0.14
    chn
    0.13
     metab
    0.12
    ough
    0.12
    uring
    0.11
    bose
    0.11
     headache
    0.10
    ongs
    0.10
     Hayden
    0.10
    Activations Density 0.006%

    No Known Activations