© 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. 33898
    Prev
    Next
    INDEX
    Explanations

    sexuality education and health services

    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
     wat
    -0.10
     Bowman
    -0.10
     kidnapping
    -0.09
     capt
    -0.09
     meth
    -0.08
     adrenaline
    -0.08
     Cutting
    -0.08
     convinc
    -0.08
    enton
    -0.08
     sob
    -0.08
    POSITIVE LOGITS
     taboo
    0.24
     openness
    0.19
     openly
    0.19
     awkward
    0.17
     educating
    0.17
     embarrassment
    0.16
     educated
    0.16
     frank
    0.16
     sexuality
    0.16
     dest
    0.16
    Activations Density 0.088%

    No Known Activations