© 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. 50931
    Prev
    Next
    INDEX
    Explanations

    all the listeners

    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
     Glad
    -0.10
    onym
    -0.09
     glad
    -0.08
     fart
    -0.08
    IDES
    -0.08
    imon
    -0.08
    lead
    -0.08
     lightning
    -0.08
    /ic
    -0.08
    ides
    -0.08
    POSITIVE LOGITS
     who
    0.11
     sweetheart
    0.10
     responses
    0.10
     contributions
    0.10
    league
    0.10
     xo
    0.10
     emailed
    0.09
     Sk
    0.09
    asma
    0.09
     involvement
    0.09
    Activations Density 0.005%

    No Known Activations