© 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. 90549
    Prev
    Next
    INDEX
    Explanations

    lung cancer

    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
     thankfully
    -0.11
     everywhere
    -0.10
    aur
    -0.08
     excell
    -0.08
     Pag
    -0.08
     Hicks
    -0.08
     excel
    -0.08
     Won
    -0.08
     mentality
    -0.08
    ide
    -0.08
    POSITIVE LOGITS
     incons
    0.11
    asan
    0.11
     Locker
    0.11
     Penal
    0.10
    erb
    0.10
    theless
    0.09
     bif
    0.09
     reimb
    0.09
     members
    0.09
    ollo
    0.09
    Activations Density 0.001%

    No Known Activations