© 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. 23483
    Prev
    Next
    INDEX
    Explanations

    game action

    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
    enet
    -0.08
    Runtime
    -0.07
    æľįè£ħ设计
    -0.07
     scont
    -0.07
    ä¸Ģ转
    -0.07
    æīĵæŀ¶
    -0.07
    »
    -0.07
    _EXTERN
    -0.07
    åĴĮéĩįçĤ¹
    -0.07
    REEN
    -0.07
    POSITIVE LOGITS
    ç»Ļ对æĸ¹
    0.08
    ìľ
    0.08
    让对æĸ¹
    0.07
    èµĦæºIJ
    0.07
    èµĦæºIJçļĦ
    0.07
    ä¸į对称
    0.07
    çŃĸçķ¥
    0.07
    eg
    0.07
    åī©ä¸ĭçļĦ
    0.07
     strategy
    0.06
    Activations Density 0.004%

    No Known Activations