© 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. 87747
    Prev
    Next
    INDEX
    Explanations

    you and yours

    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
     subdir
    -0.10
    elin
    -0.10
    rega
    -0.09
    irma
    -0.09
    angan
    -0.09
    /top
    -0.09
    uments
    -0.09
    Crud
    -0.08
    /dom
    -0.08
     Thornton
    -0.08
    POSITIVE LOGITS
     me
    0.29
     YOU
    0.26
     Yours
    0.25
     yours
    0.24
     moi
    0.23
     myself
    0.23
     ME
    0.22
     us
    0.22
    YOU
    0.21
     ours
    0.17
    Activations Density 0.204%

    No Known Activations