© 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. 14126
    Prev
    Next
    INDEX
    Explanations

    attached to or meant to be worn

    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
    Enumer
    -0.11
     contributing
    -0.10
     Äijã
    -0.09
     Bom
    -0.09
     dearly
    -0.09
     uninterrupted
    -0.09
    cad
    -0.09
    deaux
    -0.09
    -media
    -0.09
    ché
    -0.09
    POSITIVE LOGITS
     worn
    0.18
     attach
    0.18
     meant
    0.16
     intended
    0.16
     attaches
    0.15
     strapped
    0.14
     wearable
    0.14
     sits
    0.13
    attach
    0.13
    Attach
    0.12
    Activations Density 0.756%

    No Known Activations