© 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. 112596
    Prev
    Next
    INDEX
    Explanations

    abortion and related terminology

    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
    nis
    -0.12
     unh
    -0.11
    amer
    -0.11
     Jeh
    -0.11
    let
    -0.11
     Teh
    -0.10
     masturb
    -0.10
    ascar
    -0.10
    orage
    -0.10
     kissed
    -0.10
    POSITIVE LOGITS
     clinic
    0.10
    icide
    0.09
     pill
    0.09
     clinics
    0.09
     controversial
    0.09
     Clinic
    0.09
    arium
    0.08
    arer
    0.08
    ive
    0.08
     rare
    0.08
    Activations Density 0.011%

    No Known Activations