© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17188
    Prev
    Next
    INDEX
    Explanations

    nutritional requirements for adults

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    onica
    -0.22
    çĻ»
    -0.21
    æŃ£éĿ¢
    -0.20
     ÑĦоÑĢмиÑĢова
    -0.20
    ç«ĭ项
    -0.20
    éĤij
    -0.20
     пÑĢиÑıÑĤн
    -0.20
    ä¿¡å¿ĥ
    -0.20
    串
    -0.20
    âıIJ
    -0.20
    POSITIVE LOGITS
     adults
    0.28
    æĪIJ年人
    0.27
     adult
    0.26
    aget
    0.25
    _NS
    0.25
    æĪIJ人
    0.25
    ä¸ĢèĪ¬äºº
    0.24
    èĨ³é£Ł
    0.23
    æĻ®éĢļ人
    0.23
    ç»´æĮģ
    0.23
    Activations Density 0.035%

    No Known Activations