© 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. 17217
    Prev
    Next
    INDEX
    Explanations

    seething, boiling, brewing liquids

    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
     wipe
    -0.10
    lich
    -0.09
    .pull
    -0.09
     tow
    -0.09
    outh
    -0.09
     mechanically
    -0.09
    pull
    -0.09
    airs
    -0.09
     Pearson
    -0.09
     Binding
    -0.08
    POSITIVE LOGITS
     simmer
    0.27
     stew
    0.25
     boiling
    0.22
     bub
    0.22
     boil
    0.21
     brewing
    0.18
     volcano
    0.17
     boils
    0.17
     boiled
    0.17
     hotter
    0.16
    Activations Density 0.024%

    No Known Activations