© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32176
    Prev
    Next
    INDEX
    Explanations

    respect and etiquette

    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
     dangerously
    -0.11
     Require
    -0.10
     infiltr
    -0.10
     specializing
    -0.09
    serve
    -0.09
     strategically
    -0.09
     ense
    -0.09
     sell
    -0.09
     tirelessly
    -0.09
     teach
    -0.08
    POSITIVE LOGITS
     respectful
    0.27
     Respect
    0.23
     respecting
    0.21
     etiquette
    0.21
     respect
    0.20
     respectfully
    0.20
     disrespectful
    0.19
     disrespect
    0.18
     respects
    0.18
    respect
    0.18
    Activations Density 0.021%

    No Known Activations