© 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. 1442
    Prev
    Next
    INDEX
    Explanations

    traditional chinese medicine effects

    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
    æĪĸèĢħåħ¶ä»ĸ
    -0.08
    å¾Ģ
    -0.08
    вай
    -0.07
    owitz
    -0.07
    uson
    -0.07
    空çļĦ
    -0.07
    tür
    -0.07
    egd
    -0.07
    æĸĩ件æĪĸ
    -0.07
    ä¸įæĸŃæıIJåįĩ
    -0.07
    POSITIVE LOGITS
    并使
    0.08
    åħ¼
    0.07
    lect
    0.07
    并éĩį
    0.07
    CID
    0.07
    强身
    0.07
    çĶŁæ´¥
    0.06
     sekaligus
    0.06
    并为
    0.06
     elig
    0.06
    Activations Density 0.005%

    No Known Activations