© 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. 22506
    Prev
    Next
    INDEX
    Explanations

    computer system or contents

    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
    æĬĢæľ¯è¿ĽæŃ¥
    -0.06
    æĿ¾å¼Ľ
    -0.06
     stad
    -0.05
    ниÑģ
    -0.05
     maintain
    -0.05
     reasonable
    -0.05
    zer
    -0.05
     rigor
    -0.05
    éĩį度
    -0.05
     Stad
    -0.05
    POSITIVE LOGITS
    ä»İåħ¶
    0.06
    为èį£
    0.06
    ultat
    0.06
    dio
    0.06
    ç»°
    0.06
     housed
    0.06
    åħ¬å¼ĢæĭĽèģĺ
    0.06
    Think
    0.06
    å»īæ´ģ
    0.06
    воÑĢ
    0.06
    Activations Density 0.001%

    No Known Activations