© 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. 50997
    Prev
    Next
    INDEX
    Explanations

    ensure safety and proper use

    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
     wherever
    -0.11
     THEN
    -0.11
     Excell
    -0.11
    udy
    -0.10
     pronto
    -0.10
     subur
    -0.10
    ROTO
    -0.10
     KH
    -0.10
     Seen
    -0.10
    ernel
    -0.10
    POSITIVE LOGITS
     beware
    0.13
    Always
    0.13
     yourself
    0.13
     ALWAYS
    0.11
     Always
    0.11
     always
    0.11
     unfamiliar
    0.11
     remember
    0.10
    ï¼Į请
    0.10
     ensure
    0.10
    Activations Density 0.282%

    No Known Activations