© 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. 44264
    Prev
    Next
    INDEX
    Explanations

    date formats

    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
    imen
    -0.07
    sorry
    -0.07
     nächste
    -0.07
    çļĦ空éĹ´
    -0.07
    人æĹł
    -0.07
    _cycles
    -0.07
    acor
    -0.07
    ä¸ĭä¸Ģ
    -0.07
    anee
    -0.07
    éŀł
    -0.06
    POSITIVE LOGITS
    obl
    0.07
    èħĨ
    0.07
    ÏħÏĥ
    0.07
    éĿŀåħ¸
    0.07
    èµ·æĿ¥çļĦ
    0.07
    ä½łæĺ¯æĪijçļĦ
    0.07
    illery
    0.07
    便å¼Ģå§ĭ
    0.07
    _INF
    0.07
    ä¹ĭåĪĿ
    0.06
    Activations Density 0.126%

    No Known Activations