© 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. 17427
    Prev
    Next
    INDEX
    Explanations

    dignity, respect, humiliation and degradation

    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
    antha
    -0.11
     Widow
    -0.11
    orro
    -0.11
     naughty
    -0.10
     nir
    -0.10
    utton
    -0.10
    attr
    -0.10
     luk
    -0.10
     leth
    -0.10
     distracted
    -0.10
    POSITIVE LOGITS
     dignity
    0.57
     humiliation
    0.52
     humiliating
    0.51
     dign
    0.50
     humili
    0.41
     demean
    0.34
     embarrassing
    0.33
     degradation
    0.33
     degraded
    0.32
     indign
    0.32
    Activations Density 0.129%

    No Known Activations