© 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. 25221
    Prev
    Next
    INDEX
    Explanations

    have + verb participle

    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
    inp
    -0.10
     fren
    -0.09
     merit
    -0.09
    inet
    -0.09
    Handled
    -0.09
     aired
    -0.08
    inden
    -0.08
     salute
    -0.08
     integ
    -0.08
    oder
    -0.08
    POSITIVE LOGITS
     decided
    0.19
     just
    0.16
     decide
    0.15
     finally
    0.14
     tasked
    0.13
    just
    0.13
     decides
    0.13
     invited
    0.12
     Decide
    0.11
     amassed
    0.11
    Activations Density 0.227%

    No Known Activations