© 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. 46001
    Prev
    Next
    INDEX
    Explanations

    LEGO, outdoor, toy, wheel structures

    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
     Lesbian
    -0.10
     lesbian
    -0.10
     genital
    -0.10
     Jazz
    -0.09
     Rout
    -0.09
    porn
    -0.09
     raster
    -0.09
     Female
    -0.09
     ovar
    -0.09
     PCIe
    -0.08
    POSITIVE LOGITS
     knex
    0.19
     stunt
    0.13
     LEGO
    0.12
     indoors
    0.12
     outdoors
    0.12
     Outdoor
    0.11
     Evo
    0.11
     puppet
    0.11
     toy
    0.11
     outdoor
    0.11
    Activations Density 2.395%

    No Known Activations