© 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. 92474
    Prev
    Next
    INDEX
    Explanations

    opera singers and vocalists

    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
     Skate
    -0.12
     skateboard
    -0.12
     skate
    -0.11
     Violence
    -0.10
     press
    -0.09
     Tennis
    -0.09
     Bacon
    -0.09
     redistrib
    -0.09
     formulated
    -0.08
     Mens
    -0.08
    POSITIVE LOGITS
     singing
    0.58
     sung
    0.49
     singers
    0.49
     sang
    0.45
     sings
    0.45
     Sing
    0.45
     sing
    0.41
     singer
    0.40
     vocal
    0.38
     Vocal
    0.35
    Activations Density 0.677%

    No Known Activations