© 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. 4240
    Prev
    Next
    INDEX
    Explanations

    food and health benefits

    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
     bypass
    -0.10
     Gregory
    -0.10
     cath
    -0.10
     fool
    -0.10
     Goose
    -0.10
     unab
    -0.10
    warm
    -0.10
     therap
    -0.10
     therapeutic
    -0.10
     perc
    -0.10
    POSITIVE LOGITS
     sluggish
    0.15
     longevity
    0.14
     energy
    0.13
     metabolism
    0.12
     stamina
    0.12
     glowing
    0.11
     complexion
    0.11
     body
    0.11
     Energy
    0.10
     vitality
    0.10
    Activations Density 0.259%

    No Known Activations