© 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. 89085
    Prev
    Next
    INDEX
    Explanations

    balls

    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
     scrambled
    -0.13
     Pee
    -0.11
    Used
    -0.11
     nood
    -0.10
     Raq
    -0.10
    .blob
    -0.10
     scrambling
    -0.10
     scram
    -0.10
     chast
    -0.10
    aec
    -0.10
    POSITIVE LOGITS
     recipe
    0.20
     Recipe
    0.19
     made
    0.15
    recipe
    0.14
     homemade
    0.13
     Made
    0.13
     recipes
    0.13
    Recipe
    0.12
     Homemade
    0.12
    made
    0.12
    Activations Density 0.556%

    No Known Activations