© 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. 7079
    Prev
    Next
    INDEX
    Explanations

    method

    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
     confl
    -0.07
    .nlm
    -0.07
    ê±°
    -0.07
    upan
    -0.07
    ä½ľä¸ºä¸Ģ个
    -0.07
    æ¯ĶæĪij
    -0.07
    æĪĸåĪłéĻ¤
    -0.07
    ä¸įèĢIJçĥ¦
    -0.06
    åIJĥå®ĮäºĨ
    -0.06
    oid
    -0.06
    POSITIVE LOGITS
    çļĦåĪ¶ä½ľæĸ¹æ³ķ
    0.09
    è¿Ļæł·çļĦ人
    0.08
    æĸ¹æ³ķåıĬ
    0.08
    åĴĮæĸ¹æ³ķ
    0.08
    _MIX
    0.07
    ittest
    0.07
    åıĬåħ¶åºĶçĶ¨
    0.07
     methods
    0.07
    ãģĿãģĨãģ§
    0.07
    åıĬåħ¶
    0.07
    Activations Density 0.689%

    No Known Activations