© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3627
    Prev
    Next
    INDEX
    Explanations

    words ending in "-ach", "-uck", "-amp", "-ome", "-uk", "-agon", "-ug"

    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
    Negative Logits
    inic
    -0.11
    vang
    -0.11
    ickle
    -0.11
    olio
    -0.11
    uml
    -0.11
     Courtesy
    -0.11
    agos
    -0.10
     Masc
    -0.10
    ahoo
    -0.10
     numbers
    -0.10
    POSITIVE LOGITS
    gran
    0.10
     pressing
    0.09
    places
    0.08
     bore
    0.08
    lico
    0.07
     sprawling
    0.07
     broadly
    0.07
     baz
    0.07
     preceded
    0.07
     plagued
    0.07
    Activations Density 0.299%

    No Known Activations