© 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. 3484
    Prev
    Next
    INDEX
    Explanations

    stating or saying something

    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
     Avery
    -0.10
     Www
    -0.10
     ?',
    -0.10
     {})
    -0.10
     ?");↵
    -0.10
     yell
    -0.10
    ##_
    -0.10
    \č↵
    -0.10
     {}).
    -0.09
     visibly
    -0.09
    POSITIVE LOGITS
     “âĢ¦
    0.42
     “[
    0.37
     "...
    0.36
     "[
    0.31
    :↵↵
    0.29
     "..
    0.26
     Quote
    0.25
    :↵↵↵↵
    0.25
     quote
    0.24
    :"
    0.24
    Activations Density 1.820%

    No Known Activations