© 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. 3426
    Prev
    Next
    INDEX
    Explanations

    sound quality descriptions

    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
    rie
    -0.11
    pek
    -0.10
    pac
    -0.10
     Vivo
    -0.10
    @g
    -0.10
    oeff
    -0.09
    imps
    -0.09
     Boeh
    -0.09
     pregnant
    -0.09
     expecting
    -0.09
    POSITIVE LOGITS
     lamin
    0.11
     unh
    0.11
     smooth
    0.10
    bury
    0.09
     leg
    0.09
     Gran
    0.09
     crisp
    0.09
     gran
    0.08
    azy
    0.08
     nj
    0.08
    Activations Density 0.001%

    No Known Activations