© 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. 31534
    Prev
    Next
    INDEX
    Explanations

    food preference

    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
    undle
    -0.09
     Kle
    -0.09
    -hide
    -0.09
     entertainment
    -0.09
     overflowing
    -0.09
    coop
    -0.09
     rele
    -0.09
    alue
    -0.09
     entertain
    -0.08
     overcrow
    -0.08
    POSITIVE LOGITS
     tastes
    0.19
     taste
    0.19
     preference
    0.18
     preferences
    0.17
     Preference
    0.16
     staple
    0.15
     Taste
    0.14
     preferred
    0.14
    Preference
    0.14
     preferring
    0.14
    Activations Density 0.143%

    No Known Activations