© 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. 115814
    Prev
    Next
    INDEX
    Explanations

    drilling wells or holes

    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
     unwrap
    -0.13
    abox
    -0.12
     swords
    -0.11
     Swamp
    -0.11
     gated
    -0.11
     contin
    -0.10
     cot
    -0.10
    éĻ¢
    -0.10
     Ripple
    -0.10
     slashed
    -0.10
    POSITIVE LOGITS
     drilling
    0.52
     drill
    0.52
     drilled
    0.48
     Drill
    0.46
     drills
    0.42
     holes
    0.25
     boring
    0.25
     hole
    0.24
    /dr
    0.24
     bore
    0.23
    Activations Density 0.181%

    No Known Activations