© 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. 28463
    Prev
    Next
    INDEX
    Explanations

    water, bath, tub, immersion

    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
     rain
    -0.14
     locker
    -0.13
     Rain
    -0.13
     Station
    -0.13
     Spray
    -0.13
     Jog
    -0.13
     spray
    -0.12
     jogging
    -0.12
     spraying
    -0.12
     gra
    -0.12
    POSITIVE LOGITS
     submerged
    0.28
     immersion
    0.19
     immersed
    0.19
     underwater
    0.18
     floating
    0.18
     bath
    0.18
     bubbles
    0.17
     dipped
    0.17
     recl
    0.17
     flotation
    0.17
    Activations Density 0.063%

    No Known Activations