© 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. 116213
    Prev
    Next
    INDEX
    Explanations

    respect 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
    vig
    -0.10
     overpower
    -0.10
     imposing
    -0.09
     Mog
    -0.09
     Colbert
    -0.09
    entropy
    -0.09
     imposition
    -0.09
     prob
    -0.09
    Writable
    -0.09
    endor
    -0.09
    POSITIVE LOGITS
     valued
    0.12
     dignity
    0.12
     treated
    0.11
     respect
    0.10
     regardless
    0.10
     respects
    0.10
     integral
    0.10
     treat
    0.10
     recognition
    0.10
    381
    0.10
    Activations Density 0.053%

    No Known Activations