© 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. 856
    Prev
    Next
    INDEX
    Explanations

    global, electronic, school, intestinal, clinical, refugee, psychiatric, process

    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
    人ä¹ĭ
    -0.07
    AndGet
    -0.07
    人äºĨ
    -0.07
    /from
    -0.07
    ,is
    -0.07
    Ù°
    -0.06
    вÑĪейÑģÑı
    -0.06
    æĪĸä¸İ
    -0.06
    并ä¸İ
    -0.06
    使ä¹ĭ
    -0.06
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩéĥ½
    0.11
    åıĭ们
    0.11
    羣æŃ£æĪIJ为
    0.10
    åħ¬åı¸æĭ¥æľī
    0.10
    åĨħ容çĶ±
    0.10
    åħ¬åı¸å°Ĩ
    0.09
    çĪ±ä¸į
    0.09
    建设æĪIJ为
    0.09
    ä¹ĭéĹ´åŃĺåľ¨
    0.09
    è´¹çĶ¨çĶ±
    0.09
    Activations Density 0.277%

    No Known Activations