© 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. 44397
    Prev
    Next
    INDEX
    Explanations

    rice, paste, patch, card

    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
    ajer
    -0.08
    åĴĮä¿ĿæĬ¤
    -0.08
    å¦Ĥä¸Ģ
    -0.08
    oste
    -0.08
    æľ¬æĸĩéĵ¾æİ¥
    -0.08
     Bela
    -0.08
    _ATT
    -0.07
    ansir
    -0.07
    æĹłå¿Į
    -0.07
    ooth
    -0.07
    POSITIVE LOGITS
    aticon
    0.06
    纹
    0.06
    ä¸ŃåĽ½å®¶
    0.06
    åįĩ
    0.06
    æıĴä¸Ĭ
    0.06
    หลวà¸ĩ
    0.06
    æł¹æį®åĽ½å®¶
    0.06
    CT
    0.06
     ramp
    0.06
    grap
    0.06
    Activations Density 0.084%

    No Known Activations