© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5947
    Prev
    Next
    INDEX
    Explanations

    profanity

    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
     Entr
    -0.09
     cot
    -0.09
     innoc
    -0.09
     painfully
    -0.09
     pan
    -0.09
     Cot
    -0.09
     Handy
    -0.08
     Conc
    -0.08
     Pan
    -0.08
    acc
    -0.08
    POSITIVE LOGITS
     screw
    0.38
     fuck
    0.37
     Screw
    0.37
     heck
    0.35
     hell
    0.34
     Fuck
    0.30
    fuck
    0.29
    Fuck
    0.28
     sod
    0.25
     Hell
    0.24
    Activations Density 0.090%

    No Known Activations