© 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. 34128
    Prev
    Next
    INDEX
    Explanations

    show or tour

    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
     Tune
    -0.11
     repeats
    -0.10
     dictate
    -0.10
    _kw
    -0.10
     dict
    -0.09
     packing
    -0.09
     dictates
    -0.09
    dek
    -0.09
     Dec
    -0.09
     Fulton
    -0.09
    POSITIVE LOGITS
     tour
    0.26
     showcasing
    0.24
     tours
    0.23
     showing
    0.23
     showcase
    0.21
     showcases
    0.21
     showc
    0.21
     toured
    0.20
     Showing
    0.20
     show
    0.19
    Activations Density 0.118%

    No Known Activations