© 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. 47599
    Prev
    Next
    INDEX
    Explanations

    Markdown link syntax

    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
    ergestellt
    -0.10
    çļĦæĦıæĢĿæĺ¯
    -0.08
    çİ°åľ¨æĺ¯
    -0.08
    åľ°çIJĨä½įç½®ä¼ĺè¶Ĭ
    -0.08
    家æĺ¯
    -0.08
    ìĦ±ìĿĢ
    -0.08
    æ°´æĺ¯
    -0.08
    æ¯Ķèµ·
    -0.08
    å¹´æĺ¯
    -0.08
    ä»Ĭå¹´æĺ¯
    -0.08
    POSITIVE LOGITS
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.13
    æīĢ
    0.10
    æıIJåĪ°çļĦ
    0.10
    æīĢèĥ½
    0.10
    èµĸ以
    0.10
     által
    0.09
    带æĿ¥çļĦ
    0.09
    认åı¯çļĦ
    0.09
    表çİ°åĩºæĿ¥çļĦ
    0.09
    帶ä¾ĨçļĦ
    0.09
    Activations Density 0.148%

    No Known Activations