© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114931
    Prev
    Next
    INDEX
    Explanations

    oil or gas based fluids

    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
     jugg
    -0.11
     Nolan
    -0.10
     turtles
    -0.10
    eted
    -0.09
    776
    -0.09
    HK
    -0.09
     vessels
    -0.09
    stell
    -0.09
     bells
    -0.09
    ventions
    -0.09
    POSITIVE LOGITS
     alcohol
    0.14
     gasoline
    0.12
     Alcohol
    0.12
     alcoholic
    0.12
     oils
    0.12
     vinegar
    0.12
     beer
    0.12
     dry
    0.11
     saline
    0.11
     oily
    0.11
    Activations Density 0.094%

    No Known Activations