© 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. 15931
    Prev
    Next
    INDEX
    Explanations

    nephro- kidney-related 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
     Fuse
    -0.11
     bum
    -0.11
    arily
    -0.10
    pectives
    -0.10
     fier
    -0.10
    abal
    -0.10
     wrappers
    -0.10
    idan
    -0.10
    ifications
    -0.09
    bower
    -0.09
    POSITIVE LOGITS
     Nep
    0.10
    алÑĮ
    0.09
    esus
    0.09
     flair
    0.08
     succession
    0.08
    Alg
    0.08
    ½
    0.08
    roma
    0.08
     nep
    0.08
     Prescott
    0.08
    Activations Density 0.112%

    No Known Activations