© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3257
    Prev
    Next
    INDEX
    Explanations

    types of organizations and technical specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     incontro
    -0.24
    ç½ijåıĭè¯Ħ论
    -0.24
    _method
    -0.23
     lÃŃ
    -0.22
     OPTIONAL
    -0.21
    æľªç»ıæİĪæĿĥ
    -0.21
    |)↵
    -0.21
     rif
    -0.21
    _absolute
    -0.21
    Narr
    -0.20
    POSITIVE LOGITS
    ä¹ĭç±»çļĦ
    0.32
    ãģ¨ãģĦãģĨãĤĤãģ®
    0.31
    æĪĸæĺ¯
    0.28
    çŃīçŃī
    0.27
    ä¹ĭç±»
    0.26
    æĪĸåħ¶ä»ĸ
    0.25
    æĪĸèĢħåħ¶ä»ĸ
    0.25
    æĪĸèĢħæĺ¯
    0.25
    çŃī缸åħ³
    0.25
     etc
    0.24
    Activations Density 0.206%

    No Known Activations