© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54308
    Prev
    Next
    INDEX
    Explanations

    gift or gifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    请注æĦı
    -0.10
    grounds
    -0.09
    .addValue
    -0.09
     kê
    -0.09
    acco
    -0.09
    .apiUrl
    -0.08
    .ie
    -0.08
    attle
    -0.08
    æĸ°éĹ»è®°èĢħ
    -0.08
    صاص
    -0.08
    POSITIVE LOGITS
    礼çī©
    0.15
    èµłéĢģ
    0.12
     gift
    0.12
    礼åĵģ
    0.12
    è´Ī
    0.12
     gifts
    0.11
    éĢģç»Ļ
    0.11
    ãĥĹãĥ¬ãĤ¼ãĥ³ãĥĪ
    0.11
    èµł
    0.11
    é¦Ī
    0.10
    Activations Density 0.031%

    No Known Activations