© 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. 14865
    Prev
    Next
    INDEX
    Explanations

    method calls and types

    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
     než
    -0.09
    ä¹ĭ以
    -0.08
    odiac
    -0.08
    szyscy
    -0.07
    åħ¶äºĮ
    -0.07
    riad
    -0.07
    ä¹ĭäºİ
    -0.07
    emente
    -0.07
    isez
    -0.07
    lande
    -0.07
    POSITIVE LOGITS
    æŶçļĦ
    0.08
    两ä¸į误
    0.08
    èĢĮåħ¥
    0.08
    çļĦæĸ¹å¼ı
    0.08
    æĹ¶å¯¹
    0.07
    AndGet
    0.07
    èĥ½åĬĽå¼º
    0.07
    ä¸İåIJ¦
    0.07
    ypi
    0.07
    è¿ĩç¨ĭä¸Ń
    0.07
    Activations Density 0.252%

    No Known Activations