© 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. 3619
    Prev
    Next
    INDEX
    Explanations

    incapacitation, disability, paralysis

    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
     sands
    -0.08
    inst
    -0.08
     eyebrows
    -0.08
     ked
    -0.08
    142
    -0.08
    rud
    -0.08
     skipped
    -0.08
    Con
    -0.07
     nowhere
    -0.07
     disputed
    -0.07
    POSITIVE LOGITS
     crippling
    0.16
     cripp
    0.15
     crippled
    0.14
    /inc
    0.14
     handic
    0.13
     immobil
    0.13
    ingly
    0.12
     handicap
    0.12
     disables
    0.12
    /arm
    0.11
    Activations Density 0.160%

    No Known Activations