© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61783
    Prev
    Next
    INDEX
    Explanations

    explaining or adding details

    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
    eding
    -0.07
    nga
    -0.07
    ä¸ĢæľĿ
    -0.07
    elok
    -0.06
    ä¸Ģ
    -0.06
    à¦Ļà§įà¦Ĺ
    -0.06
    å¢ĥå¤ĸè¾ĵåħ¥
    -0.06
    uert
    -0.06
     diversos
    -0.06
    ijIJ
    -0.06
    POSITIVE LOGITS
    çļĦåħ¶ä»ĸ
    0.09
    åħ¶ä»ĸçļĦ
    0.09
    åħ¶ä»ĸæĸ¹å¼ı
    0.08
     additional
    0.08
    æĢ§æĪĸ
    0.08
    è¿ĺåı¯èĥ½
    0.08
     other
    0.08
    åħ¶å®ĥçļĦ
    0.08
     otras
    0.08
    人æĪĸ
    0.08
    Activations Density 0.047%

    No Known Activations