© 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. 10582
    Prev
    Next
    INDEX
    Explanations

    synthesis of compounds

    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
    èĨ
    -0.21
    _hdl
    -0.20
    phia
    -0.20
     hiá»ĩp
    -0.20
    ç»ĥ
    -0.18
    ä»»ä½ķæŶåĢĻ
    -0.18
    onaut
    -0.18
    vant
    -0.18
    æ²ģ
    -0.18
    @class
    -0.18
    POSITIVE LOGITS
    æĸ¹æ³ķ
    0.28
    éĢĶå¾Ħ
    0.28
    æŃ¥éª¤
    0.28
    第ä¸ĢæŃ¥
    0.28
    è¿ĩç¨ĭ
    0.28
    è¿ĩç¨ĭä¸Ń
    0.26
    ä¸ĢæŃ¥
    0.25
    è¿Ļç§įæĸ¹æ³ķ
    0.25
    å·¥ä¸ļåĮĸ
    0.24
    çļĦæĸ¹æ³ķ
    0.24
    Activations Density 0.264%

    No Known Activations