© 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. 39010
    Prev
    Next
    INDEX
    Explanations

    world, life, day, body, system, internet

    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
    æľ¬äººåľ¨
    -0.09
     phấn
    -0.09
    åľ¨æķ´ä¸ª
    -0.09
    åľ¨éĩĮéĿ¢
    -0.09
    ông
    -0.08
    iou
    -0.08
    åħ¨åĽ½äººæ°ij
    -0.08
    åħ¨åİ¿
    -0.08
    iado
    -0.08
    äºİäºĭ
    -0.08
    POSITIVE LOGITS
    -wide
    0.12
    wide
    0.10
    åĴĮä¼ģä¸ļ
    0.09
    åIJĦå¤Ħ
    0.08
    åħ¶ä»ĸåľ°æĸ¹
    0.08
    æ¯ıä¸Ģ个è§ĴèIJ½
    0.08
    æ·±å¤ĦçļĦ
    0.08
    éĩĮçļĦ
    0.08
    åĴĮ家åºŃ
    0.07
    å¤ļ个
    0.07
    Activations Density 0.447%

    No Known Activations