© 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. 28097
    Prev
    Next
    INDEX
    Explanations

    stigmatized or stigma

    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
    rox
    -0.08
     booming
    -0.08
     Ire
    -0.08
    .retry
    -0.08
     crush
    -0.08
     grip
    -0.08
     pros
    -0.08
    velle
    -0.08
     swore
    -0.08
     strengths
    -0.08
    POSITIVE LOGITS
     stigma
    0.19
     unfairly
    0.17
     attached
    0.14
     Profession
    0.13
     labeling
    0.13
    /social
    0.13
     attaching
    0.13
     associ
    0.13
     attaches
    0.12
     unjust
    0.12
    Activations Density 0.029%

    No Known Activations