© 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. 3323
    Prev
    Next
    INDEX
    Explanations

    time to

    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
     Proceed
    -0.25
    并åıij
    -0.23
     obtains
    -0.21
    Rand
    -0.21
    éĢģå¾Ģ
    -0.21
    æĸ¹åľĨ
    -0.20
    åıĬåħ¶ä»ĸ
    -0.20
    è¦ĨçĽĸçİĩ
    -0.20
    头éĥ¨
    -0.20
    loses
    -0.19
    POSITIVE LOGITS
    ä»Ķç»Ĩ
    0.32
    æĢĿèĢĥ
    0.30
    审è§Ĩ
    0.29
    yme
    0.28
    ä½ĵä¼ļ
    0.27
    è®¤çľŁ
    0.26
    ç»Ĩç»Ĩ
    0.26
    æĥ³äºĨæĥ³
    0.26
    æĥ³æĥ³
    0.26
    ç»Ĩèĩ´
    0.26
    Activations Density 0.016%

    No Known Activations