© 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. 8213
    Prev
    Next
    INDEX
    Explanations

    can't + verb

    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
     dare
    -0.10
     dared
    -0.10
     forgiving
    -0.10
     departure
    -0.10
     compliments
    -0.09
     gladly
    -0.09
    wcs
    -0.09
     forgive
    -0.09
     Pioneer
    -0.09
     forg
    -0.09
    POSITIVE LOGITS
     expect
    0.13
     blamed
    0.12
     underestimate
    0.12
     selectively
    0.12
     outr
    0.11
     blame
    0.11
     undo
    0.10
     fault
    0.10
    anh
    0.10
     expecting
    0.10
    Activations Density 0.085%

    No Known Activations