© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49653
    Prev
    Next
    INDEX
    Explanations

    preventing fluid ingress

    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
    Not in Any Lists

    No Comments

    Negative Logits
     shaped
    -0.10
     acl
    -0.10
     ties
    -0.10
     Shapes
    -0.10
     grop
    -0.09
     tether
    -0.09
    aes
    -0.09
     tires
    -0.09
     shape
    -0.09
     attachments
    -0.09
    POSITIVE LOGITS
     electronics
    0.21
     electrical
    0.19
     electronic
    0.18
     Electronics
    0.17
     Electrical
    0.17
     internals
    0.16
     moisture
    0.16
     ingress
    0.15
     Electronic
    0.14
    electronics
    0.14
    Activations Density 0.075%

    No Known Activations