© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37340
    Prev
    Next
    INDEX
    Explanations

    food and nourishment

    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
    ç³ĸæŀľ
    -0.11
    åĸľæ¬¢åIJĥ
    -0.11
    è¿Ľé£Ł
    -0.10
    é£Łåĵģ
    -0.10
    飯
    -0.10
    .food
    -0.10
     اÙĦطعاÙħ
    -0.10
    meal
    -0.10
    é¥Ń
    -0.09
     foods
    -0.09
    POSITIVE LOGITS
    æ¡¥æ¢ģ
    0.09
    _syn
    0.08
    磾
    0.08
    ç¿İ
    0.08
     Sloan
    0.08
    æ¢Ń
    0.08
    OrDefault
    0.08
     Jet
    0.08
    èĭĩ
    0.08
    íķŃ
    0.08
    Activations Density 0.107%

    No Known Activations