© 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. 111941
    Prev
    Next
    INDEX
    Explanations

    people and gendered terms

    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
     Patt
    -0.09
    -turned
    -0.09
    -origin
    -0.09
    ados
    -0.09
     TL
    -0.08
    TL
    -0.08
     refere
    -0.08
    elves
    -0.08
    ork
    -0.08
    gener
    -0.08
    POSITIVE LOGITS
    alo
    0.10
     Alone
    0.10
     homme
    0.10
    isz
    0.10
    illon
    0.10
    -wh
    0.10
     Awake
    0.10
    Fatal
    0.10
     Rare
    0.10
     rare
    0.09
    Activations Density 0.019%

    No Known Activations