© 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. 34064
    Prev
    Next
    INDEX
    Explanations

    would + 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
     would
    -0.14
    'd
    -0.12
    mania
    -0.11
    ’d
    -0.10
    enez
    -0.10
    would
    -0.10
     Would
    -0.10
    /bind
    -0.10
     wards
    -0.10
    -ish
    -0.10
    POSITIVE LOGITS
    nt
    0.33
     be
    0.26
    -be
    0.22
    /c
    0.20
    NT
    0.19
    ’ve
    0.18
    've
    0.17
    nts
    0.16
     probably
    0.15
    /w
    0.15
    Activations Density 0.092%

    No Known Activations