© 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. 34913
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
    缴æİ¥æĪĸ
    -0.07
    转载æĪĸ
    -0.07
    æĸĩ件æĪĸ
    -0.07
     chÄĥng
    -0.07
    ãģ§ãģĹãĤĩãģĨãģĭ
    -0.07
     либо
    -0.06
    å¤įåĪ¶æĪĸ
    -0.06
    æĬķèµĦæĪĸ
    -0.06
    ille
    -0.06
    æį
    -0.06
    POSITIVE LOGITS
    çī¹æĦı
    0.10
    suggest
    0.08
     seemingly
    0.08
    ãĤıãģĸãĤıãģĸ
    0.08
    å¹¶ä½ľ
    0.08
    说æĺİ
    0.08
     ausdrücklich
    0.07
     deliberately
    0.07
    uggest
    0.07
    并积æŀģ
    0.07
    Activations Density 0.016%

    No Known Activations