© 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. 88328
    Prev
    Next
    INDEX
    Explanations

    pornography and censorship laws

    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
     imperson
    -0.09
     jumper
    -0.09
     telemetry
    -0.09
     adorable
    -0.09
     gluten
    -0.09
     romantic
    -0.09
     allergy
    -0.09
     Garmin
    -0.08
     allerg
    -0.08
     sentimental
    -0.08
    POSITIVE LOGITS
     censorship
    0.25
     Porn
    0.24
     pornography
    0.24
     porn
    0.23
    Porn
    0.23
     Media
    0.22
    porn
    0.20
    Media
    0.20
     MEDIA
    0.19
     censor
    0.19
    Activations Density 0.248%

    No Known Activations