© 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. 63011
    Prev
    Next
    INDEX
    Explanations

    space or part of a word

    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
    æķħéĩĮ
    -0.07
     handy
    -0.07
     gai
    -0.07
    æ§Ľ
    -0.06
    ä¼
    -0.06
    chern
    -0.06
    éĻĦ表
    -0.06
    ساÙĨ
    -0.06
    轩
    -0.06
     indirectly
    -0.06
    POSITIVE LOGITS
    åijĪçİ°åĩº
    0.10
     ressemble
    0.10
    evin
    0.09
     resemble
    0.09
    çļĦå½¢çĬ¶
    0.09
     resembles
    0.09
     resembled
    0.08
    çļĦæĺ¯ä¸Ģ个
    0.08
     berbentuk
    0.08
    å®ĥæĺ¯ä¸Ģ个
    0.08
    Activations Density 0.033%

    No Known Activations