© 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. 30675
    Prev
    Next
    INDEX
    Explanations

    offensive language

    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
     BuzzFeed
    -0.10
     WB
    -0.10
     ppl
    -0.10
     Kardashian
    -0.10
    Âł
    -0.09
    ubi
    -0.09
     FB
    -0.09
     gonna
    -0.09
     hashtag
    -0.09
     YA
    -0.09
    POSITIVE LOGITS
     retarded
    0.11
     Karn
    0.11
     retard
    0.11
     zam
    0.10
     shemale
    0.10
    _prec
    0.10
     Stap
    0.10
     jade
    0.10
     cripp
    0.10
    SITE
    0.10
    Activations Density 0.020%

    No Known Activations