© 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. 3133
    Prev
    Next
    INDEX
    Explanations

    industry overhaul or companies

    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
    åij½åIJį为
    -0.30
     photograph
    -0.28
     printed
    -0.28
     accidentally
    -0.27
     instruction
    -0.27
    让å®ĥ
    -0.27
     Lingu
    -0.26
    å¥ĩå¦Ļ
    -0.26
     Literary
    -0.26
     copyrighted
    -0.26
    POSITIVE LOGITS
    å¸ĤåľºçļĦ
    0.37
    åŃĺéĩı
    0.37
    å¸Ĥåľº
    0.35
    åĩłå®¶
    0.34
    çŃĸçķ¥
    0.34
    éĻįä»·
    0.34
    éľĢæ±Ĥ
    0.33
    ä½İä»·
    0.33
    纷纷
    0.32
    è¾ĥä½İ
    0.32
    Activations Density 0.051%

    No Known Activations