© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4256
    Prev
    Next
    INDEX
    Explanations

    terrorist attacks and bombings

    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
    å·¡è§Ĩåijĺ
    -0.07
    wana
    -0.07
    å¢ŀåĢ¼çĶµä¿¡ä¸ļåĬ¡ç»ıèIJ¥è®¸åı¯è¯ģ
    -0.07
    容æĺĵ产çĶŁ
    -0.07
    .arg
    -0.07
     thừa
    -0.07
    转载æĪĸå¼ķçĶ¨
    -0.07
    转载æĪĸ
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.07
    åģ·åģ·
    -0.07
    POSITIVE LOGITS
    è¢Ńåĩ»
    0.12
     targeting
    0.11
    襲
    0.10
     perpetrated
    0.10
     terrorist
    0.09
    attacks
    0.09
     atent
    0.09
     bombings
    0.09
     terrorism
    0.09
    è¢Ń
    0.09
    Activations Density 0.222%

    No Known Activations