© 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. 29926
    Prev
    Next
    INDEX
    Explanations

    ethics and behavior

    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
    embr
    -0.12
     shel
    -0.11
    inka
    -0.11
    escape
    -0.10
     corrective
    -0.10
     Assets
    -0.10
     paradox
    -0.09
     assets
    -0.09
    IFS
    -0.09
     fearing
    -0.09
    POSITIVE LOGITS
     ethical
    0.32
     unethical
    0.30
     ethics
    0.29
     Ethics
    0.27
    ethical
    0.24
     disrespectful
    0.23
     morally
    0.23
     eth
    0.22
     ethic
    0.21
     etiquette
    0.21
    Activations Density 0.125%

    No Known Activations