© 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. 4117
    Prev
    Next
    INDEX
    Explanations

    offensive 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
     transc
    -0.10
     esposa
    -0.09
     Sands
    -0.09
     NEC
    -0.09
     soph
    -0.09
     Fulton
    -0.09
     cheat
    -0.08
     Kor
    -0.08
     Heard
    -0.08
    ifest
    -0.08
    POSITIVE LOGITS
     Onc
    0.10
     paran
    0.10
     Gra
    0.10
     oro
    0.10
     incidental
    0.09
    ubber
    0.09
     Bü
    0.09
     Capital
    0.09
    /display
    0.09
     competing
    0.09
    Activations Density 0.001%

    No Known Activations