© 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. 3312
    Prev
    Next
    INDEX
    Explanations

    character description or action

    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
    çĻ½éĽª
    -0.27
     Gör
    -0.25
    å°ijä¸įäºĨ
    -0.25
    综
    -0.23
    åľ¨ä»Ĭå¹´
    -0.23
    æŶéĻIJ
    -0.23
    æ¯ĶåĪĨ
    -0.23
    ä¼ļä¸įä¼ļ
    -0.23
    çݯæ¯Ķ
    -0.23
    åĢ¼å¾Ĺä¸Ģ
    -0.22
    POSITIVE LOGITS
     trag
    0.26
     transformed
    0.26
    éķ¿éĢĶ
    0.24
     incarnation
    0.24
    ä¸į幸
    0.24
    深深
    0.23
    åĪº
    0.23
    UEST
    0.23
    CLAIM
    0.23
     embodies
    0.23
    Activations Density 0.061%

    No Known Activations