© 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. 20284
    Prev
    Next
    INDEX
    Explanations

    outcomes and achievement

    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
    æĺ¯å¾Ī
    -0.08
    为佳
    -0.08
    aron
    -0.07
    è¿Ļä¹Łæĺ¯
    -0.07
    æĺ¯å¾Īéĩįè¦ģçļĦ
    -0.07
    ä¸ºå®ľ
    -0.07
    她å¾Ī
    -0.07
     поло
    -0.06
    éĥ½å¾Ī好
    -0.06
    çļĦ为
    -0.06
    POSITIVE LOGITS
    ä¾Ŀèµĸäºİ
    0.11
     relies
    0.11
    å¾Ī大ç¨ĭ度ä¸Ĭ
    0.10
    åıĸåĨ³äºİ
    0.10
    ä¸įåľ¨äºİ
    0.10
     hinges
    0.10
     depends
    0.09
    ä¸įä»ħéľĢè¦ģ
    0.09
     primarily
    0.09
    çļĦåħ³éĶ®
    0.09
    Activations Density 0.161%

    No Known Activations