© 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. 87846
    Prev
    Next
    INDEX
    Explanations

    instrumental or dehumanizing object

    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
     vigil
    -0.08
    -court
    -0.08
     underst
    -0.08
     modest
    -0.08
     outr
    -0.08
     cheek
    -0.08
     ar
    -0.08
     principio
    -0.08
     neighbors
    -0.08
     retr
    -0.07
    POSITIVE LOGITS
     interchangeable
    0.25
     commodity
    0.21
     disposable
    0.21
     commodities
    0.20
     mere
    0.19
     expend
    0.18
     merely
    0.17
     convenient
    0.16
     commod
    0.16
     Disposable
    0.15
    Activations Density 0.060%

    No Known Activations