© 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. 92638
    Prev
    Next
    INDEX
    Explanations

    worry or concern

    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
     bored
    -0.12
    Demand
    -0.10
    etten
    -0.09
    dden
    -0.09
     defiance
    -0.09
    oho
    -0.09
     greeting
    -0.09
     Demand
    -0.09
    grily
    -0.08
     aggression
    -0.08
    POSITIVE LOGITS
     worry
    0.71
     worries
    0.70
     worried
    0.66
     fears
    0.64
     concern
    0.62
     concerns
    0.60
     fear
    0.59
     worrying
    0.58
     feared
    0.57
     Concern
    0.55
    Activations Density 0.676%

    No Known Activations