© 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. 50657
    Prev
    Next
    INDEX
    Explanations

    adoption and fostering

    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
     misogyn
    -0.11
     subordinate
    -0.10
     compliment
    -0.10
     husbands
    -0.10
    eid
    -0.10
    hai
    -0.10
    izen
    -0.09
     capitals
    -0.09
    -mini
    -0.09
     pne
    -0.09
    POSITIVE LOGITS
     adoption
    0.45
     Adoption
    0.44
     adopt
    0.41
     orphan
    0.39
     Adopt
    0.38
     adopted
    0.36
    adopt
    0.33
     foster
    0.31
     adopting
    0.30
     adopts
    0.30
    Activations Density 0.423%

    No Known Activations