© 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. 117286
    Prev
    Next
    INDEX
    Explanations

    autism spectrum disorder ASD

    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
    utility
    -0.09
     pap
    -0.09
     utility
    -0.09
     dap
    -0.09
     MX
    -0.09
     dissent
    -0.09
     Gn
    -0.08
     mx
    -0.08
    jad
    -0.08
    ìĬ
    -0.08
    POSITIVE LOGITS
     autism
    0.46
     autistic
    0.45
     Autism
    0.45
     ASD
    0.34
     socially
    0.32
     social
    0.28
    -social
    0.25
    Aut
    0.25
     Aut
    0.25
     awkward
    0.24
    Activations Density 0.193%

    No Known Activations