© 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. 88164
    Prev
    Next
    INDEX
    Explanations

    profanity, profiler, professor, profane

    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
    per
    -0.10
     Boys
    -0.09
    file
    -0.09
    leton
    -0.09
    ibold
    -0.09
    perc
    -0.08
    icles
    -0.08
    orph
    -0.08
    field
    -0.08
    fields
    -0.08
    POSITIVE LOGITS
    anity
    0.15
    essed
    0.13
    sed
    0.11
    ships
    0.11
    ship
    0.11
    iciencies
    0.10
    ionales
    0.10
    ently
    0.10
    usion
    0.10
    sap
    0.10
    Activations Density 0.064%

    No Known Activations