© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11385
    Prev
    Next
    INDEX
    Explanations

    impotent patients or syncope

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ril
    -0.21
    ä¸Ģæ³¢
    -0.21
    说å®Į
    -0.19
    女è£ħ
    -0.18
    ç»·
    -0.18
    åĢ¼å¾Ĺä¸Ģ
    -0.17
     conte
    -0.17
    âŃķ
    -0.17
    伸åĩº
    -0.17
    eros
    -0.17
    POSITIVE LOGITS
    åİŁåĽł
    0.37
    çļĦåİŁåĽł
    0.34
    åİŁåĽłä¹ĭä¸Ģ
    0.34
    åİŁåĽłæĺ¯
    0.31
    主è¦ģåİŁåĽł
    0.30
    æĺ¯åĽłä¸º
    0.27
     ìĿ´ìľł
    0.26
    éĹ®é¢ĺ
    0.25
     due
    0.24
     caused
    0.24
    Activations Density 0.489%

    No Known Activations