© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30774
    Prev
    Next
    INDEX
    Explanations

    talking about Brent or Cake

    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
    æĽ´éĩįè¦ģçļĦæĺ¯
    -0.07
    æĽ´éĩįè¦ģçļĦ
    -0.07
    åıĪåľ¨
    -0.07
    asa
    -0.07
     perhaps
    -0.07
    åıĪä¸įèĥ½
    -0.07
    åıĪä¸į
    -0.07
     maybe
    -0.07
     frankly
    -0.06
    åıĪè¦ģ
    -0.06
    POSITIVE LOGITS
    å°±æĺ¯è¿Ļä¹Ī
    0.10
    åıªä¸įè¿ĩ
    0.09
    åıªä¸įéģİ
    0.08
    å°±æĺ¯è¿Ļæł·
    0.08
     itulah
    0.07
     inilah
    0.07
    ä¸įè¿ĩä»ĸ
    0.07
     $('[
    0.07
    è¿ĻæŃ£æĺ¯
    0.07
     coincid
    0.07
    Activations Density 0.004%

    No Known Activations