© 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. 48784
    Prev
    Next
    INDEX
    Explanations

    chemical ingredients and polymers

    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
     antid
    -0.12
    mint
    -0.11
     sculpture
    -0.11
    artisan
    -0.10
     sculpt
    -0.10
     mint
    -0.10
     poisoned
    -0.10
     Dop
    -0.10
    onet
    -0.10
     Sculpt
    -0.10
    POSITIVE LOGITS
     oils
    0.19
     ingredient
    0.15
     starch
    0.14
     gly
    0.14
     Vegetable
    0.14
    PEG
    0.13
     Oil
    0.13
     insol
    0.13
     oil
    0.13
     petroleum
    0.13
    Activations Density 1.590%

    No Known Activations