© 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. 16643
    Prev
    Next
    INDEX
    Explanations

    recommendations or options

    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
    æĺ¯éĿŀ
    -0.06
    ä¸įèĩ³äºİ
    -0.05
    读
    -0.05
     formula
    -0.05
     ren
    -0.05
    Lf
    -0.05
    ainment
    -0.04
     descon
    -0.04
     Voc
    -0.04
    кл
    -0.04
    POSITIVE LOGITS
     existi
    0.07
    بÙĬر
    0.07
    æĺµ
    0.07
    ilea
    0.07
    éĺ¿åĵ¥
    0.07
    voy
    0.06
    å¿ĥçĶĺ
    0.06
     intelek
    0.06
    cules
    0.06
    obra
    0.06
    Activations Density 0.024%

    No Known Activations