© 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. 18771
    Prev
    Next
    INDEX
    Explanations

    sexual tension and elite roles

    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
     peoples
    -0.08
     gut
    -0.08
    747
    -0.08
    eras
    -0.07
     televised
    -0.07
     Edwin
    -0.07
     brain
    -0.07
    era
    -0.07
     equity
    -0.07
     conditioning
    -0.07
    POSITIVE LOGITS
     rhet
    0.13
     penetr
    0.13
     Petr
    0.12
     rhetorical
    0.12
     ux
    0.12
     arist
    0.12
     renegot
    0.11
     elite
    0.11
     Pen
    0.11
     reput
    0.11
    Activations Density 0.060%

    No Known Activations