© 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. 111752
    Prev
    Next
    INDEX
    Explanations

    autism spectrum, developmental disabilities, employment

    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
     afflict
    -0.13
     suffering
    -0.11
     suffer
    -0.11
     suffers
    -0.10
     suffered
    -0.10
     reconstruction
    -0.10
     lame
    -0.10
     knee
    -0.10
     injuries
    -0.10
     crippled
    -0.09
    POSITIVE LOGITS
     autistic
    0.18
     Autism
    0.18
     autism
    0.17
     mainstream
    0.15
     caregivers
    0.14
     wheelchair
    0.13
     Medicaid
    0.13
     aba
    0.13
     caregiver
    0.13
     sensory
    0.12
    Activations Density 1.586%

    No Known Activations