© 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. 18755
    Prev
    Next
    INDEX
    Explanations

    foster family adoption

    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
     mimic
    -0.10
     mim
    -0.09
     imitation
    -0.09
     REM
    -0.08
     resisted
    -0.08
    uta
    -0.08
     peas
    -0.08
     lag
    -0.08
    arel
    -0.08
    asar
    -0.08
    POSITIVE LOGITS
     mentoring
    0.19
     resc
    0.18
     treating
    0.18
     sponsoring
    0.18
     mentor
    0.18
     caring
    0.18
     treat
    0.16
     custody
    0.16
     guardians
    0.16
     treats
    0.16
    Activations Density 0.235%

    No Known Activations