© 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. 33300
    Prev
    Next
    INDEX
    Explanations

    explaining reasons why

    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
    ä¼łæĿ¥
    -0.07
    ä¸Ģæ´¾
    -0.07
    é£İèµ·
    -0.06
     conting
    -0.06
    å¦į
    -0.06
    åıĸå¾ĹèĥľåĪ©
    -0.06
    谨记
    -0.06
    æĺ¾å¾ĹæľīäºĽ
    -0.06
    æĹ¨åľ¨
    -0.06
    ç¨įç¨į
    -0.06
    POSITIVE LOGITS
     unique
    0.11
    çĭ¬ä¸ĢæĹłäºĮçļĦ
    0.11
    çĭ¬çī¹çļĦ
    0.11
     Ñĥника
    0.10
    çĭ¬çī¹
    0.10
    çļĦçĭ¬çī¹
    0.10
    跻身
    0.10
     surpassed
    0.09
    unique
    0.09
    åĽłä¸ºåħ¶
    0.09
    Activations Density 0.282%

    No Known Activations