© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19449
    Prev
    Next
    INDEX
    Explanations

    spa massage and wellness treatments

    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
    祢
    -0.09
    ç²īç¢İ
    -0.09
    elmet
    -0.09
    笼
    -0.09
    åļı
    -0.09
    å¼Ģæ°´
    -0.08
    meter
    -0.08
    icap
    -0.08
    æĹĹå¸ľ
    -0.08
    _startup
    -0.08
    POSITIVE LOGITS
    æĮīæij©
    0.18
     massage
    0.15
     Massage
    0.14
    æĬ¤èĤ¤
    0.13
    çļ®èĤ¤
    0.12
     massages
    0.11
    ç¾İ容
    0.11
     Spa
    0.11
     spa
    0.11
    spa
    0.10
    Activations Density 0.099%

    No Known Activations