© 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. 6961
    Prev
    Next
    INDEX
    Explanations

    gift received or given

    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
    eren
    -0.09
    aju
    -0.09
    alem
    -0.09
    iene
    -0.09
     carriers
    -0.09
     Reviewed
    -0.09
     hereby
    -0.09
     getContent
    -0.09
    elay
    -0.09
    -dependent
    -0.08
    POSITIVE LOGITS
     gift
    0.30
     gifted
    0.28
     purchased
    0.28
     bought
    0.26
     gifts
    0.26
     Gift
    0.25
     donated
    0.25
     acquired
    0.24
    gift
    0.23
     obtained
    0.23
    Activations Density 0.289%

    No Known Activations