© 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. 32566
    Prev
    Next
    INDEX
    Explanations

    knowledge and definitions

    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
    è¿ĺä¼ļåĩºçİ°
    -0.09
     Psychiat
    -0.09
    éĹ®é¢ĺä¸Ĭ
    -0.09
    æľ¬é¢ĺåĪĨæŀIJ
    -0.08
    iture
    -0.08
     intelekt
    -0.08
    ä½łæķ¢
    -0.08
    æĮģä¹ĭ以
    -0.08
    ิà¹Īม
    -0.08
    åıĸåħ¶
    -0.08
    POSITIVE LOGITS
    åŁºæľ¬çļĦ
    0.09
     definitions
    0.08
     basics
    0.08
    æľīåħ³äºİ
    0.07
     bahwa
    0.07
    ä»Ģä¹Īæĺ¯
    0.07
    åŁºæľ¬æ¦Ĥ念
    0.07
    å®ļä¹ī
    0.07
    åŁºæľ¬çŁ¥è¯Ĩ
    0.07
     principles
    0.07
    Activations Density 0.079%

    No Known Activations