© 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. 62370
    Prev
    Next
    INDEX
    Explanations

    media coverage and attention

    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
    åİŁåľ°
    -0.07
     deposits
    -0.07
     deposited
    -0.07
    ä¸ĭ表
    -0.07
    ATAN
    -0.07
    åĨħ容æıIJä¾Ľæĸ¹
    -0.07
    çĤ¹çĤ¹å¤´
    -0.06
    å¯ĦåŃĺ
    -0.06
    æij¸ç´¢
    -0.06
    atan
    -0.06
    POSITIVE LOGITS
     attention
    0.10
    å¹¿æ³Ľåħ³æ³¨
    0.10
    åħ³æ³¨çļĦçĦ¦çĤ¹
    0.09
    æĮģç»Ńåħ³æ³¨
    0.09
    çĤĴä½ľ
    0.09
    åªĴä½ĵçļĦ
    0.09
     media
    0.09
    ä¸Ģéĺµéĺµ
    0.09
    èĪĨ论
    0.09
    çĦ¦çĤ¹
    0.09
    Activations Density 0.358%

    No Known Activations