© 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. 56307
    Prev
    Next
    INDEX
    Explanations

    sitting in a room

    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
    èĢħä¹Ł
    -0.09
     outright
    -0.08
    ussi
    -0.08
    妨ç¢į
    -0.08
    è¾ĥ强çļĦ
    -0.07
    æĺİæĺ¾
    -0.07
    人ä¹ĭ
    -0.07
     gimm
    -0.07
    åĢ¾åIJijäºİ
    -0.07
    Observers
    -0.07
    POSITIVE LOGITS
    ä¸Ģå¼łå¼ł
    0.08
    ä¸Ģ次次
    0.08
    æ¯ıä¸Ģ次
    0.08
    æĺ¯å¤ļä¹Ī
    0.07
    -debug
    0.07
    cket
    0.07
     flick
    0.07
    éĤ£ä¸ĢåĪ»
    0.06
    ä¸ĵçĶ¨çļĦ
    0.06
    meister
    0.06
    Activations Density 0.475%

    No Known Activations