© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 3434
    Prev
    Next
    INDEX
    Explanations

    sexual content

    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
    Negative Logits
     fluctuations
    -0.10
     stripped
    -0.10
     fluct
    -0.09
    stri
    -0.09
     Shirt
    -0.09
     stripper
    -0.09
     Hatch
    -0.09
     clothing
    -0.09
     clothes
    -0.09
     camouflage
    -0.09
    POSITIVE LOGITS
     anal
    0.17
     anatom
    0.16
     penetration
    0.16
     taboo
    0.16
     Anal
    0.14
     penetr
    0.14
     rear
    0.14
     preferences
    0.14
     insertion
    0.13
     anus
    0.13
    Activations Density 0.064%

    No Known Activations