© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19608
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    è®
    -0.05
     BI
    -0.05
    çľ¼åīįçļĦ
    -0.05
    cestor
    -0.05
    -led
    -0.05
    yers
    -0.05
    oled
    -0.05
    大éĩıçļĦ
    -0.04
    yper
    -0.04
    çĶŁ
    -0.04
    POSITIVE LOGITS
    äºİè¡Į
    0.07
    åĪ°åºķ
    0.06
    äºİ人
    0.06
    åī¯ç§ĺ书éķ¿
    0.06
    czÄĻÅĽciej
    0.06
     aanb
    0.06
    è°ĵ
    0.06
    èĥ½è¾¾åĪ°
    0.05
    主ä½ĵå·¥ç¨ĭ
    0.05
     Afinal
    0.05
    Activations Density 0.000%

    No Known Activations