© 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. 25184
    Prev
    Next
    INDEX
    Explanations

    will, would, could

    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
    inel
    -0.11
     unh
    -0.10
    sed
    -0.10
    iren
    -0.10
    asty
    -0.09
    bru
    -0.09
    Eu
    -0.09
     pep
    -0.09
    enment
    -0.09
    acher
    -0.09
    POSITIVE LOGITS
    /how
    0.13
    kommen
    0.10
    licht
    0.09
     fres
    0.08
     enough
    0.08
     anything
    0.08
    ow
    0.08
     fantast
    0.08
     their
    0.08
    owing
    0.08
    Activations Density 0.039%

    No Known Activations