© 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. 5046
    Prev
    Next
    INDEX
    Explanations

    dam and reservoir

    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
     spir
    -0.13
     Arbor
    -0.11
     jit
    -0.11
     jogging
    -0.11
     Roots
    -0.11
     Brewing
    -0.11
    roots
    -0.10
     Root
    -0.10
     sour
    -0.10
     configur
    -0.10
    POSITIVE LOGITS
     dam
    0.44
     dams
    0.40
     Dam
    0.33
    dam
    0.30
    Dam
    0.29
     reservoir
    0.28
     DAM
    0.25
     flood
    0.22
     upstream
    0.20
     Flood
    0.19
    Activations Density 0.214%

    No Known Activations