© 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. 47896
    Prev
    Next
    INDEX
    Explanations

    embarrassment and shame

    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
     percept
    -0.12
     safest
    -0.11
    âĦ
    -0.10
     Falcon
    -0.10
     omin
    -0.10
     safer
    -0.10
     vig
    -0.10
     Gale
    -0.10
     dangerously
    -0.10
     progn
    -0.10
    POSITIVE LOGITS
     shame
    0.46
     embarrassment
    0.44
     Shame
    0.42
     ashamed
    0.39
     humiliation
    0.38
     shameful
    0.38
     embarrassed
    0.37
     embarrass
    0.36
     embarrassing
    0.35
     humiliating
    0.32
    Activations Density 0.097%

    No Known Activations