© 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. 7788
    Prev
    Next
    INDEX
    Explanations

    gift for others

    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
     conven
    -0.10
    logan
    -0.10
    èIJ
    -0.09
    enan
    -0.09
    agina
    -0.09
     Grove
    -0.09
    roman
    -0.09
     Outs
    -0.09
     shame
    -0.09
    ivan
    -0.09
    POSITIVE LOGITS
     gift
    0.66
     gifts
    0.60
     Gift
    0.55
     Gifts
    0.52
    gift
    0.51
    Gift
    0.50
     gifted
    0.42
    _gift
    0.39
     Christmas
    0.33
     birthday
    0.32
    Activations Density 0.367%

    No Known Activations