© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44736
    Prev
    Next
    INDEX
    Explanations

    trade secrets or wildlife

    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
    Negative Logits
    aum
    -0.06
    åħįè´¹é¢Ĩåıĸ
    -0.06
    åį«è®¡å§Ķ
    -0.06
    åłĤçļĩ
    -0.06
    วาส
    -0.06
    åľ°äºļ
    -0.06
    å½ķåıĸåĪĨæķ°çº¿
    -0.05
    端åºĦ
    -0.05
     à¹Ģà¸Ńà¸ģ
    -0.05
    ware
    -0.05
    POSITIVE LOGITS
    å°ıåŃIJ
    0.09
    UserCode
    0.07
    è¿Ļå°ıåŃIJ
    0.07
    "She
    0.07
     benne
    0.07
    çĭĹä»Ķ
    0.07
    Slinky
    0.07
    িà¦ķà§įষ
    0.06
    éĵ¿
    0.06
    汽车éĶĢåĶ®æľįåĬ¡æľīéĻIJåħ¬åı¸
    0.06
    Activations Density 7.797%

    No Known Activations