© 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. 18230
    Prev
    Next
    INDEX
    Explanations

    chemical reactions and biological processes

    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
    è¿Ļç§įåģļæ³ķ
    -0.08
    浩çĦ¶
    -0.07
    æŁIJäºĽ
    -0.07
    epro
    -0.07
    æļĹæļĹ
    -0.07
    æĮº
    -0.07
    ()._
    -0.07
    stücke
    -0.06
     Nhĩ
    -0.06
    earer
    -0.06
    POSITIVE LOGITS
    ankind
    0.07
    å¾ĭå·±
    0.07
     inex
    0.07
    ä»»ä½ķå½¢å¼ıçļĦ
    0.07
    æ¡ĤåĨł
    0.06
    å±ŀåľ°
    0.06
    æĺ¯äººç±»
    0.06
    çIJĨ论åŃ¦ä¹ł
    0.06
    æĹłçŁ¥
    0.06
    .xhtml
    0.06
    Activations Density 0.234%

    No Known Activations