© 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. 92034
    Prev
    Next
    INDEX
    Explanations

    recipe or concoction

    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
     intact
    -0.11
    aille
    -0.10
    pref
    -0.10
    inte
    -0.09
     pled
    -0.09
     inflated
    -0.09
     Sears
    -0.09
     etiqu
    -0.09
    INY
    -0.09
     eating
    -0.09
    POSITIVE LOGITS
     recipe
    0.47
     recipes
    0.39
     Recipe
    0.37
    recipe
    0.35
     conco
    0.33
     Recipes
    0.33
    Recipe
    0.32
     formula
    0.32
     mixture
    0.30
     ingredients
    0.29
    Activations Density 0.453%

    No Known Activations