© 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. 117581
    Prev
    Next
    INDEX
    Explanations

    often oneself

    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
     now
    -0.15
    æĪijçļĦ
    -0.15
     my
    -0.13
     myself
    -0.13
     unprecedented
    -0.12
     tonight
    -0.12
     here
    -0.12
     again
    -0.11
     ahora
    -0.10
    .springboot
    -0.10
    POSITIVE LOGITS
     oneself
    0.19
     often
    0.11
     Often
    0.11
     sometimes
    0.11
     preferably
    0.11
     usually
    0.11
     themselves
    0.10
     yourself
    0.10
    aye
    0.10
     spouse
    0.10
    Activations Density 0.512%

    No Known Activations