© 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. 28718
    Prev
    Next
    INDEX
    Explanations

    sections, parts, or items

    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
    åĩºçİ°åľ¨
    -0.09
    åıijçĶŁåľ¨
    -0.09
    ä¹ĭäºİ
    -0.08
    表çİ°åľ¨
    -0.08
    åŃĺåľ¨äºİ
    -0.08
    ä¸Ĭæ·»
    -0.08
    èĥĮå¾Į
    -0.08
    åĩºçı¾åľ¨
    -0.08
    æĮĤåľ¨
    -0.08
    æĬĢæľ¯åľ¨
    -0.08
    POSITIVE LOGITS
    çļĦ身影
    0.09
    çĦī
    0.08
     namanya
    0.08
     Dort
    0.07
     dort
    0.07
    è¿Ľåİ»
    0.07
    лÑĭп
    0.07
    å½¢æĪIJäºĨä¸Ģ个
    0.07
     AllÃŃ
    0.07
    æĦŁåıĹçĿĢ
    0.07
    Activations Density 0.262%

    No Known Activations