© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5979
    Prev
    Next
    INDEX
    Explanations

    capacitive touch panel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    çī¹æ´¾
    -0.11
    éĵ§
    -0.09
    çķļ
    -0.09
    è¿Ļæīįæĺ¯
    -0.09
    å£ģ
    -0.08
    CLU
    -0.08
    é¦ĸè½®
    -0.08
     Parm
    -0.08
    çĶ¨å¿ĥ
    -0.08
    æĸĩåĮĸåºķèķ´
    -0.08
    POSITIVE LOGITS
    é¢Ŀ头
    0.10
    è¿Ļå¼ł
    0.10
    宿
    0.09
    zell
    0.09
    æĩ¦
    0.09
    Globals
    0.09
    æ·Į
    0.08
    æľīæľº
    0.08
    bon
    0.08
     Flesh
    0.08
    Activations Density 0.209%

    No Known Activations