© 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. 16769
    Prev
    Next
    INDEX
    Explanations

    tunnel-diode, VA-API-utils, arcade machine

    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
    å·¥ç¨ĭè¿Ľåº¦
    -0.06
    çijľ
    -0.05
     proš
    -0.05
    лдÑĭ
    -0.05
    оÑĩ
    -0.05
    éŀ
    -0.05
    issi
    -0.05
    ç¥
    -0.05
     myself
    -0.05
     bout
    -0.05
    POSITIVE LOGITS
    Fx
    0.05
    hir
    0.05
    è¿ľè·Ŀ离
    0.05
    chas
    0.05
    æĿ¡
    0.05
    ä¸Ńæĸ°
    0.05
    origine
    0.05
    è¿ľåľ¨
    0.05
    ramer
    0.05
    it
    0.05
    Activations Density 0.074%

    No Known Activations