© 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. 27205
    Prev
    Next
    INDEX
    Explanations

    expletive-laden muttering or cursing

    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
    modo
    -0.11
    oir
    -0.10
     fla
    -0.10
     insistence
    -0.10
    275
    -0.10
     Hayden
    -0.09
    conda
    -0.09
    ACHE
    -0.09
     trans
    -0.09
     insisted
    -0.09
    POSITIVE LOGITS
     curse
    0.45
     curses
    0.45
     curs
    0.44
     cursed
    0.41
     swearing
    0.35
     swear
    0.33
     muttered
    0.32
     Curse
    0.32
     swore
    0.30
     mut
    0.28
    Activations Density 0.116%

    No Known Activations