© 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. 47894
    Prev
    Next
    INDEX
    Explanations

    proud or ashamed expressions

    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
     subjective
    -0.11
    PCS
    -0.11
     movers
    -0.09
    underline
    -0.09
    ppe
    -0.09
    ona
    -0.09
    olson
    -0.09
    /per
    -0.09
    elay
    -0.09
    adel
    -0.09
    POSITIVE LOGITS
     proud
    0.52
     pride
    0.46
     Proud
    0.42
     ashamed
    0.38
     Pride
    0.38
     proudly
    0.36
     shame
    0.28
     embarrassed
    0.27
     shameful
    0.25
     embarrassment
    0.25
    Activations Density 0.104%

    No Known Activations