© 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. 2178
    Prev
    Next
    INDEX
    Explanations

    chairman, page, she, he, you

    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
    hias
    -0.08
    严éĩįæŶ
    -0.08
     ,[
    -0.07
    æīĢå±ŀåĪĨç±»
    -0.07
    åİĨéĻ©
    -0.07
    å¿ħè¦ģæŶ
    -0.07
    以ä¸ĭæĺ¯å°ıç¼ĸ
    -0.07
    ç³»çļĦ
    -0.07
    ",-
    -0.07
    unde
    -0.07
    POSITIVE LOGITS
    éĿŀ常çļĦ
    0.07
    æĽ´åĬłçļĦ
    0.07
    ws
    0.07
    è¿Ļä¸ªæľºä¼ļ
    0.07
    ilet
    0.07
    è¿Ļæł·ä¸Ģç§į
    0.06
    ä»»ä½ķçļĦ
    0.06
    人们对äºİ
    0.06
    çĥŃåĬĽ
    0.06
    æīĢæľīçļĦ人
    0.06
    Activations Density 0.058%

    No Known Activations