© 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. 3373
    Prev
    Next
    INDEX
    Explanations

    woman needs

    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
     Laurent
    -0.11
     guys
    -0.10
     Guys
    -0.09
     msm
    -0.09
     Dough
    -0.08
     Asi
    -0.08
    chy
    -0.08
     +'
    -0.08
     advance
    -0.08
    advance
    -0.08
    POSITIVE LOGITS
    iac
    0.11
    ADA
    0.10
     serious
    0.10
     unreal
    0.10
     practically
    0.10
     needs
    0.10
     DR
    0.10
     multit
    0.10
     Gem
    0.10
     enjoys
    0.10
    Activations Density 0.024%

    No Known Activations