© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63874
    Prev
    Next
    INDEX
    Explanations

    diet

    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
    Negative Logits
    çĶŁäº§æĢ»
    -0.09
    è¡¥é½IJ
    -0.09
    æ¾į
    -0.09
    纡
    -0.09
    çģ¾
    -0.09
    emble
    -0.09
    çģ½
    -0.09
    å¿ĥ头
    -0.08
     Relax
    -0.08
    anio
    -0.08
    POSITIVE LOGITS
    é¥®é£Ł
    0.17
     diet
    0.16
     Diet
    0.15
     diets
    0.14
    diet
    0.14
    æijĦ
    0.12
    éĻIJåĪ¶
    0.11
    饮
    0.11
    èį¤
    0.10
    é£Łçī©
    0.10
    Activations Density 0.146%

    No Known Activations