© 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. 43057
    Prev
    Next
    INDEX
    Explanations

    exchange and barter

    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
    Gre
    -0.09
    heu
    -0.08
    éĺħè§Ī室
    -0.08
    æĭīèµ·
    -0.08
    å°Ķå¤ļ
    -0.08
    rong
    -0.08
    ãģ¤ãĤĤãĤĬ
    -0.08
    uard
    -0.08
    -library
    -0.08
    /sources
    -0.08
    POSITIVE LOGITS
    ä»·åĢ¼
    0.09
    åķĨåĵģçļĦ
    0.09
    交æį¢
    0.09
     exchange
    0.08
    æµģéĢļ
    0.08
    åĩĿç»ĵ
    0.08
    åķĨåĵģ
    0.08
     exchanged
    0.08
     Exchange
    0.07
    ä»·åĢ¼çļĦ
    0.07
    Activations Density 0.004%

    No Known Activations