© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49790
    Prev
    Next
    INDEX
    Explanations

    respects for people, rights, and dignity

    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
    Not in Any Lists

    No Comments

    Negative Logits
     satisfying
    -0.12
     Dun
    -0.11
    BM
    -0.10
     pleasing
    -0.10
    mente
    -0.10
     Satisfaction
    -0.10
     benefiting
    -0.10
     intrig
    -0.09
    /utility
    -0.09
     gle
    -0.09
    POSITIVE LOGITS
     privacy
    0.13
     integrity
    0.13
     wishes
    0.11
     dignity
    0.10
     enough
    0.10
     autonomy
    0.10
     decisions
    0.09
     sanct
    0.09
    obao
    0.09
    pu
    0.09
    Activations Density 0.028%

    No Known Activations