© 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. 15852
    Prev
    Next
    INDEX
    Explanations

    pornographic actors and studios

    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
     stationary
    -0.11
     Barber
    -0.11
     gastr
    -0.11
     Shirt
    -0.10
    .gb
    -0.10
    æľį
    -0.10
    conscious
    -0.10
    .fb
    -0.10
     Gian
    -0.10
     FOOT
    -0.10
    POSITIVE LOGITS
     Models
    0.11
     models
    0.10
    XXX
    0.10
     industry
    0.10
     pessim
    0.10
    Models
    0.10
     churn
    0.09
    .xxx
    0.09
     Boiler
    0.09
     strip
    0.09
    Activations Density 0.220%

    No Known Activations