© 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. 30936
    Prev
    Next
    INDEX
    Explanations

    soap in web services or surfactants

    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
    urge
    -0.08
     paint
    -0.08
     squash
    -0.08
     sprink
    -0.07
     hemos
    -0.07
    _VC
    -0.07
    åº
    -0.07
    lear
    -0.07
     icing
    -0.07
     shallow
    -0.07
    POSITIVE LOGITS
     soap
    0.25
     SOAP
    0.24
     Soap
    0.23
    Soap
    0.21
    SOAP
    0.20
    soap
    0.19
     detergent
    0.18
     sud
    0.17
    .SO
    0.16
     Sud
    0.16
    Activations Density 0.274%

    No Known Activations