© 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. 41601
    Prev
    Next
    INDEX
    Explanations

    Chinese herbal medicine

    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
    çݯä¿ĿæĦıè¯Ĩ
    -0.08
    å°½éĩıåĩıå°ij
    -0.07
    å°½éĩıå°ij
    -0.07
    illar
    -0.07
    inti
    -0.07
    çIJµ
    -0.07
    راÙģ
    -0.07
    _DEFIN
    -0.07
    alf
    -0.07
    æ´»ä¸ĭåİ»
    -0.07
    POSITIVE LOGITS
     versatile
    0.11
     versatility
    0.10
    å¹¿æ³ĽçĶ¨äºİ
    0.08
    åı¯ä»¥çĶ¨äºİ
    0.08
    æľ¬åĵģ
    0.08
    çĶ¨æ³ķ
    0.08
    使çĶ¨æŶ
    0.08
    åĬŁæķĪ
    0.08
    åı¯çĶ¨äºİ
    0.07
     vielseit
    0.07
    Activations Density 0.010%

    No Known Activations