© 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. 117412
    Prev
    Next
    INDEX
    Explanations

    types or kinds

    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
     Goodman
    -0.09
     Bir
    -0.08
    ÑĤо
    -0.07
    vs
    -0.07
    OrDefault
    -0.07
    ObjectId
    -0.07
    Objects
    -0.07
     Cour
    -0.07
     Hera
    -0.07
     tqdm
    -0.07
    POSITIVE LOGITS
     types
    0.76
     type
    0.75
    ç±»åŀĭ
    0.57
     kinds
    0.55
    type
    0.55
     Types
    0.54
    -types
    0.54
    types
    0.54
     kind
    0.50
    Types
    0.50
    Activations Density 1.613%

    No Known Activations