© 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. 49108
    Prev
    Next
    INDEX
    Explanations

    medical care, genome, microcavity, BBB, DM, MR

    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
    eli
    -0.11
    ioni
    -0.10
     sno
    -0.10
    (ele
    -0.09
    ymb
    -0.09
    inta
    -0.09
    hari
    -0.09
     Crom
    -0.09
    mdl
    -0.08
    imits
    -0.08
    POSITIVE LOGITS
    rib
    0.11
     insets
    0.10
     Pow
    0.10
     Bread
    0.10
    inery
    0.09
    avin
    0.09
    illes
    0.09
    bread
    0.09
    Newsletter
    0.09
    ÃŃt
    0.09
    Activations Density 0.001%

    No Known Activations