© 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. 22629
    Prev
    Next
    INDEX
    Explanations

    peer-reviewed documents and elections

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.05
    å°±è¿ŀ
    -0.05
    ؤÙĦاء
    -0.05
    ãģĦãĤĭ
    -0.05
    æ±ģ
    -0.05
    ä¸ĢæĮ¥
    -0.05
    åĴĮåŁ¹åħ»
    -0.05
    جعÙĦ
    -0.05
    å§ĭ
    -0.05
    对ä»ĺ
    -0.05
    POSITIVE LOGITS
    èĽī
    0.07
    ault
    0.07
    ìłij
    0.07
    erweise
    0.07
    cox
    0.06
    вен
    0.06
    èļ£
    0.06
    utati
    0.06
    inda
    0.06
    centes
    0.06
    Activations Density 0.003%

    No Known Activations