© 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. 5736
    Prev
    Next
    INDEX
    Explanations

    gift, gifts, or gift certificate

    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
     unins
    -0.10
     reservoir
    -0.09
    ASA
    -0.08
     saddened
    -0.08
    proto
    -0.08
     subsidi
    -0.08
     ging
    -0.08
    fusion
    -0.08
     Rally
    -0.08
    Uploaded
    -0.08
    POSITIVE LOGITS
     gift
    0.16
     Gift
    0.16
    Gift
    0.15
    gift
    0.13
     Gifts
    0.12
     giver
    0.12
     bestowed
    0.11
     unwrap
    0.11
     gifts
    0.11
     recipient
    0.11
    Activations Density 0.075%

    No Known Activations