© 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. 54954
    Prev
    Next
    INDEX
    Explanations

    Casablanca, mitochondria|DC cells, centers deliver, crest, conference, Pashleys serve

    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
    æıIJé«ĺèĩªå·±çļĦ
    -0.06
     dura
    -0.06
    æĺ¯ä»¥
    -0.06
    amay
    -0.06
    以大
    -0.06
    onor
    -0.06
    ä¹ŁåįģåĪĨ
    -0.06
    lingen
    -0.06
    åįģåĪĨ
    -0.06
    以å¢ŀåĬł
    -0.06
    POSITIVE LOGITS
    ä½ľä¸ºä¸Ģ款
    0.09
    ä½ľä¸º
    0.09
    被èªī为
    0.09
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ķัว
    0.09
    ä½ľä¸ºä¸ŃåĽ½
    0.08
    ä¼ļæĪIJ为
    0.08
    èĻ½å°ı
    0.08
    ãĤ¤ãĥĦ
    0.08
    èĥ½æĪIJ为
    0.08
    ä½ľä¸ºä¸Ģç§į
    0.08
    Activations Density 0.193%

    No Known Activations