© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16491
    Prev
    Next
    INDEX
    Explanations

    children and parenting

    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
    erno
    -0.10
     imperson
    -0.10
     Participants
    -0.09
     Cour
    -0.09
     Guys
    -0.09
     personal
    -0.09
     losers
    -0.09
    Drink
    -0.09
    dain
    -0.09
     fatigue
    -0.08
    POSITIVE LOGITS
     parenting
    0.40
     parental
    0.34
     parents
    0.33
     Parents
    0.31
    Parents
    0.29
     Parent
    0.29
     parent
    0.29
    Parent
    0.27
    parents
    0.27
    -parent
    0.26
    Activations Density 0.369%

    No Known Activations