© 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. 91406
    Prev
    Next
    INDEX
    Explanations

    medical conditions suffixity

    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
    :[[
    -0.11
     oversh
    -0.10
    _helpers
    -0.10
     Burgess
    -0.10
    /workspace
    -0.10
    ohan
    -0.10
    /meta
    -0.10
    [__
    -0.10
     NotImplemented
    -0.10
     neighbours
    -0.10
    POSITIVE LOGITS
     reputed
    0.08
     coun
    0.08
     ful
    0.08
     ,,
    0.08
    eten
    0.07
     denn
    0.07
     specular
    0.07
     resil
    0.07
    rame
    0.07
     Atkins
    0.07
    Activations Density 0.025%

    No Known Activations