© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16675
    Prev
    Next
    INDEX
    Explanations

    Commerce related suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    sta
    -0.07
    åħ·ä½ĵéĹ®é¢ĺ
    -0.07
    æĽ´åĬłå¼º
    -0.06
    èĥ½æīĵ
    -0.06
    åıĪä¸įèĥ½
    -0.06
    echa
    -0.06
     devrez
    -0.06
     Åijket
    -0.06
    ustra
    -0.06
    xEA
    -0.06
    POSITIVE LOGITS
     ar
    0.05
    ÙĪÙĩ
    0.05
    Ø·ÙĦ
    0.05
    æĶ¯æĮģåĴĮ
    0.05
     isolated
    0.05
    0.05
    å°ijçļĦ
    0.04
    -
    0.04
    unch
    0.04
    é£ŁåĵģåĴĮ
    0.04
    Activations Density 0.008%

    No Known Activations