© 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. 55781
    Prev
    Next
    INDEX
    Explanations

    love and affection expression

    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
    欣åĸľ
    -0.09
    à´·
    -0.09
    åĬŁåĬ³
    -0.09
    å¾ģæ±ĤæĦıè§ģ
    -0.09
    ç³Ł
    -0.08
    çķĻä½ı
    -0.08
    æѦåĬŁ
    -0.08
    å¼Ģåĩº
    -0.08
    èī¯å¿ĥ
    -0.08
     Dexter
    -0.08
    POSITIVE LOGITS
    sitemap
    0.11
    å½¼æѤ
    0.10
    æĥ³å¿µ
    0.09
    éļĺ
    0.09
    æ´»ä¸ĭåİ»
    0.09
    çĪ±ä½ł
    0.09
    åĩºåıij
    0.09
    åı¯æĥ³
    0.08
    éĦ£
    0.08
    缸çĪ±
    0.08
    Activations Density 0.028%

    No Known Activations