© 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. 22305
    Prev
    Next
    INDEX
    Explanations

    command and statement

    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
    leness
    -0.07
     affairs
    -0.07
    è¿ħ鼷ä¸ĭè½½
    -0.07
    çĽ¸å¯¹åºĶ
    -0.07
    اÙĨØ´
    -0.07
    åı·æĸĩ件
    -0.06
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.06
     affair
    -0.06
    为å®ŀçİ°
    -0.06
    æ¨ĭ
    -0.06
    POSITIVE LOGITS
    ä½ķçŃī
    0.07
    åľ¨è¿Ļæł·çļĦ
    0.07
     Globals
    0.07
    é»ĺ认çļĦ
    0.07
    æīĢçĶ¨
    0.07
    @"
    0.07
    ä¸Ģå¸Ĩé£İ顺
    0.07
     ê³¼ìłķìĹIJìĦľ
    0.07
     ê²°ê³¼ê°Ģ
    0.07
     indiscrim
    0.07
    Activations Density 0.054%

    No Known Activations