© 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. 115632
    Prev
    Next
    INDEX
    Explanations

    gift or giving

    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
     placeholders
    -0.10
     exploits
    -0.09
    .LINE
    -0.09
    enger
    -0.09
    crest
    -0.09
    aris
    -0.09
     todd
    -0.09
    UTE
    -0.09
     Hammond
    -0.09
    regation
    -0.09
    POSITIVE LOGITS
     gift
    0.61
     Gift
    0.48
     gifts
    0.45
    gift
    0.43
    Gift
    0.39
     gifted
    0.35
     Gifts
    0.34
    _gift
    0.29
     cade
    0.20
     giver
    0.19
    Activations Density 0.115%

    No Known Activations