© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112993
    Prev
    Next
    INDEX
    Explanations

    impaired/impairment related to glucose or energy

    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
     primal
    -0.09
    owing
    -0.09
    ALLY
    -0.09
    ynos
    -0.09
     amat
    -0.09
    iais
    -0.08
    ivan
    -0.08
    iers
    -0.08
     Appeal
    -0.08
    .hd
    -0.08
    POSITIVE LOGITS
    etus
    0.14
    ment
    0.13
    ments
    0.12
     doom
    0.11
    eding
    0.10
    issor
    0.10
    asse
    0.10
    ulsive
    0.10
    ioned
    0.10
    å¼ı
    0.09
    Activations Density 0.155%

    No Known Activations