© 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. 19547
    Prev
    Next
    INDEX
    Explanations

    unique, different, next

    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
    Not in Any Lists

    No Comments

    Negative Logits
     whatever
    -0.06
    whatever
    -0.06
    è±Ĩ
    -0.05
     kies
    -0.05
    ascÄĥ
    -0.05
    ATAR
    -0.05
    éĺ¶æ®µæĢ§
    -0.05
    éĩİ
    -0.05
     whichever
    -0.05
     respe
    -0.05
    POSITIVE LOGITS
    -next
    0.06
     improvis
    0.06
    èĩªæĭĶ
    0.06
    æĺ¯ä¸įåı¯
    0.06
    è·Łäºº
    0.05
    人ä¸İ人ä¹ĭéĹ´
    0.05
    鼷åIJĮ
    0.05
    à¸Ĭร
    0.05
     непов
    0.05
    ä¸įå±¥è¡Į
    0.05
    Activations Density 0.023%

    No Known Activations