© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46830
    Prev
    Next
    INDEX
    Explanations

    on

    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
     dear
    -0.06
    æĹłè®ºåľ¨
    -0.06
    家家
    -0.06
    oros
    -0.06
    ä¸ĢèĤ¡
    -0.06
    è¿Ļä½į
    -0.06
    åľ¨åħ¶ä»ĸ
    -0.06
    å¤ĸæı´
    -0.06
    æĹłè®ºæĺ¯åľ¨
    -0.06
     quick
    -0.06
    POSITIVE LOGITS
     entire
    0.11
     entirety
    0.10
    urna
    0.09
    æķ´ä¸ª
    0.09
    äºĨæķ´ä¸ª
    0.09
    æķ´åĢĭ
    0.08
     swath
    0.08
    èѦå±Ģ
    0.08
     từng
    0.08
    è¯Ħä»·ä½ĵç³»
    0.08
    Activations Density 0.014%

    No Known Activations