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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39569
    Prev
    Next
    INDEX
    Explanations

    food additives and preservatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    浪费æŶéĹ´
    -0.07
    itto
    -0.07
    认é¢Ĩ
    -0.07
    ularan
    -0.07
    æİ¥è¯Ĭ
    -0.07
    upert
    -0.07
    è¡Ģéĩı
    -0.07
    æ¶ī
    -0.07
    该软件
    -0.06
    اÙĩ
    -0.06
    POSITIVE LOGITS
    æ·»åĬł
    0.12
     additives
    0.12
    ä¸Ńæ·»åĬł
    0.11
    æ·»åĬłåĪ°
    0.10
    åīĤ
    0.10
    -added
    0.09
    æ·»åĬłåīĤ
    0.09
    æ·»åĬłäºĨ
    0.09
    å¾®éĩı
    0.09
     добавки
    0.09
    Activations Density 0.177%

    No Known Activations