© 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. 59134
    Prev
    Next
    INDEX
    Explanations

    contact information or evaluation

    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
    æĺ¯åĢ¼å¾Ĺ
    -0.07
    Da
    -0.07
    å°ĬéĩįåĴĮ
    -0.06
    da
    -0.06
     da
    -0.06
     Da
    -0.06
    åĬłå¥½åıĭ
    -0.06
    åĴĮäºĮ
    -0.06
    æĺ¯å¾Īæľī
    -0.06
    åħ¨ä½ĵ
    -0.06
    POSITIVE LOGITS
     zugleich
    0.08
    /or
    0.08
    两ä¸į误
    0.08
    èĬ±éĥ½
    0.07
    omu
    0.07
    ัà¸Ļà¸Ĺ
    0.07
    é¦Ī
    0.07
     ï½¢
    0.07
    ortable
    0.07
    /etc
    0.07
    Activations Density 0.517%

    No Known Activations