© 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. 34872
    Prev
    Next
    INDEX
    Explanations

    `@returns` descriptions

    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
    ç»´æĸ¯
    -0.08
    haw
    -0.07
    åıĪ以
    -0.07
    èIJ¨æĭī
    -0.07
    åıĪåľ¨
    -0.07
     ÏĢλη
    -0.07
    xBC
    -0.07
    ÑĢем
    -0.07
    Õ»
    -0.07
    åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    POSITIVE LOGITS
    æĥķ
    0.07
     _(
    0.07
    çıĤ
    0.07
    åŃĹ
    0.07
     {@
    0.06
    ullo
    0.06
    ená
    0.06
    ÙĨÚ¯
    0.06
     ()=>
    0.06
    ActionResult
    0.06
    Activations Density 0.001%

    No Known Activations