© 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. 47492
    Prev
    Next
    INDEX
    Explanations

    animal meat products

    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
     pollen
    -0.13
     sip
    -0.13
     bottle
    -0.12
     coffee
    -0.12
     glasses
    -0.12
     Bottle
    -0.11
     Glasses
    -0.11
     bottles
    -0.11
     drinking
    -0.11
     Coffee
    -0.11
    POSITIVE LOGITS
     meat
    0.54
     Meat
    0.49
     meats
    0.39
     beef
    0.39
     butcher
    0.39
     Beef
    0.36
     slaughter
    0.36
     flesh
    0.34
     carne
    0.31
     pork
    0.30
    Activations Density 0.384%

    No Known Activations