© 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. 13040
    Prev
    Next
    INDEX
    Explanations

    Chinese decoctions and blood circulation

    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
    åħįäºİ
    -0.07
    гей
    -0.07
    ä¸įèĩªç¦ģ
    -0.07
    elves
    -0.07
    éĺ²æļij
    -0.06
    èĢĥæĭī
    -0.06
     Carousel
    -0.06
    ivu
    -0.06
    witz
    -0.06
    веÑģ
    -0.06
    POSITIVE LOGITS
    çĺĢ
    0.11
    è¡Ģæµģ
    0.10
    è¡Ģ
    0.10
    æ´»è¡ĢåĮĸçĺĢ
    0.10
    blood
    0.10
    è¡ĢçļĦ
    0.10
     blood
    0.09
    æ´»è¡Ģ
    0.08
    ä¸įçķħ
    0.08
    åĩºè¡Ģ
    0.08
    Activations Density 0.004%

    No Known Activations