© 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. 49345
    Prev
    Next
    INDEX
    Explanations

    manifested or resulting states

    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
    羣æŃ£æĬĬ
    -0.07
    èĢĥå¯Ł
    -0.06
     kapit
    -0.06
     Tent
    -0.06
    æĺİç¡®äºĨ
    -0.06
     tempt
    -0.06
    æŃ£å¼ı
    -0.06
    enk
    -0.06
    è¥
    -0.06
    iston
    -0.06
    POSITIVE LOGITS
    表çݰ为
    0.15
    çļĦ表çİ°
    0.11
     resulting
    0.11
     manifested
    0.11
     produces
    0.10
    表çİ°åĩºæĿ¥
    0.10
    主è¦ģ表çݰ为
    0.10
    表çİ°åľ¨
    0.10
    导èĩ´
    0.09
    å°±ä¼ļåĩºçİ°
    0.09
    Activations Density 0.033%

    No Known Activations