© 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. 13850
    Prev
    Next
    INDEX
    Explanations

    conditioned association

    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
    airo
    -0.10
    mar
    -0.10
    ayo
    -0.10
    azzo
    -0.10
    hg
    -0.10
     revealing
    -0.10
     Raqqa
    -0.09
    modo
    -0.09
    validate
    -0.09
     Nack
    -0.09
    POSITIVE LOGITS
     association
    0.49
     associations
    0.46
     associ
    0.46
     associate
    0.45
     associates
    0.39
    association
    0.38
     Associ
    0.36
     assoc
    0.36
     Associations
    0.35
    associ
    0.34
    Activations Density 0.353%

    No Known Activations