© 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. 88213
    Prev
    Next
    INDEX
    Explanations

    adding water

    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
     Shack
    -0.11
    plex
    -0.10
    cki
    -0.10
     favicon
    -0.10
     Intersection
    -0.10
    .tar
    -0.09
     Smoke
    -0.09
     Crane
    -0.09
     hic
    -0.09
     dumpster
    -0.09
    POSITIVE LOGITS
     water
    0.36
    water
    0.25
     WATER
    0.25
     Water
    0.23
    Water
    0.23
    æ°´
    0.23
    -water
    0.22
     waters
    0.20
    _water
    0.20
    .water
    0.20
    Activations Density 0.571%

    No Known Activations