© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87680
    Prev
    Next
    INDEX
    Explanations

    slurs and insults

    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
    Negative Logits
     dang
    -0.13
     vibes
    -0.12
     darn
    -0.12
     gossip
    -0.12
     vibe
    -0.12
     OG
    -0.11
     crazy
    -0.11
     TBD
    -0.11
     stuff
    -0.11
     naughty
    -0.10
    POSITIVE LOGITS
     retarded
    0.22
     retard
    0.19
     autistic
    0.17
     autism
    0.16
     Troll
    0.14
     lul
    0.14
     Autism
    0.13
     raping
    0.13
     sper
    0.13
     FUCK
    0.13
    Activations Density 0.036%

    No Known Activations