© 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. 18640
    Prev
    Next
    INDEX
    Explanations

    eject/expel liquid or substance

    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
     chop
    -0.11
     Chop
    -0.11
    bau
    -0.10
     mole
    -0.10
     cir
    -0.09
     chopped
    -0.09
     Dise
    -0.09
     hass
    -0.09
    .minecraft
    -0.09
     dangling
    -0.09
    POSITIVE LOGITS
     drib
    0.20
     spraying
    0.20
     spill
    0.19
     discharge
    0.18
     ejac
    0.17
     eject
    0.17
     dri
    0.17
     spray
    0.17
     spills
    0.17
     ejaculation
    0.16
    Activations Density 0.112%

    No Known Activations