© 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. 22623
    Prev
    Next
    INDEX
    Explanations

    scores like 7-6

    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
    è¿Ľè¡Į交æĺĵ
    -0.06
    orang
    -0.06
    éĩįè¦ģçļĦæĺ¯
    -0.06
    ãģ£ãģ¦ãģ¿ãģ¾ãģĹãģŁ
    -0.05
    สล
    -0.05
    å¦Ĥ鼨
    -0.05
    à¥Į
    -0.05
    举æŃ¢
    -0.05
    inke
    -0.05
    æĪ´åı£ç½©
    -0.05
    POSITIVE LOGITS
    tek
    0.06
    ç»ĵæĻ¶
    0.05
    ä¹ħèĢĮ
    0.05
    ä¸İæĻ®éĢļ
    0.05
    lots
    0.05
    è´¨
    0.05
    bart
    0.05
    èĬĤ
    0.05
    anches
    0.05
    gov
    0.05
    Activations Density 0.002%

    No Known Activations